Integrative OMICs Analysis for Human Pancreatic Islets
PI Charlotte Ling, Lund University
Nikolay Oskolkov, SciLifeLab, NBIS Long Term Support, nikolay.oskolkov@scilifelab.se
January 21, 2020
Abstract
Here we will use all available sources of molecular and clinical information, i.e. OMICs data, for building a linear data integration model using the DIABLO method from mixOmics Bioconductor package that essentially represents a multi-modal extension of the PLS-DA model. The analysis will be done for 110 selected individuals with overlapping OMICs. Accuracy of T2D classification will be addressed as a criterian of integration and the confidence intervals of the prediction will be built by random splitting the 110 individuals data set into train and test multiple times.
The List of 110 Selected Individuals
All the analysis will be performed on the 110 individuals which were selected based on multiple criteria such as 1) they are either normo-glycimic or hyper-glycemic / T2D individuals, 2) they have information from all the 4 OMICS (methylation, transcriptomics, phenotypes, genotypes), 3) they all fall within the same age category, and a few other minor criteria. Now we will read the list of those 110 individuals and display a few of them:
set.seed(1)
selected_ind<-scan("OVERLAPPING_110_SAMPLES_4OMICS.txt", what = "charater")
selected_ind<-paste0("ID",selected_ind)
print(head(selected_ind, 20))## [1] "ID1" "ID3" "ID4" "ID6" "ID8" "ID10" "ID14" "ID19" "ID21" "ID30"
## [11] "ID32" "ID34" "ID35" "ID36" "ID38" "ID39" "ID44" "ID46" "ID55" "ID58"print(tail(selected_ind, 20))## [1] "ID136" "ID156" "ID160" "ID165" "ID168" "ID172" "ID175" "ID182"
## [9] "ID183" "ID191" "ID194" "ID200" "ID209" "ID210" "ID214" "ID217"
## [17] "ID221" "ID228" "ID263" "ID273"Preparing Data for Feature Pre-Selection
Here we are going to read each of the 4 OMICs data sets and perform some basic filtering and harmonization for further Feature Pre-Selection step. This step is needed in order to avoid the Curse of Dimensionality problem, i.e. we need to reduce dimensions of each OMIC before putting them together into the integrative DIABLO PLS-DA model.
We start with loading expression, methylation, genotype and phenotype data sets for the selected 110 individuals with all 4 OMICs overlapping. Previously those OMICs were cleaned, log-transformed and prepared for integration.
library("matrixStats")
expr<-read.table("Integr_Expr.txt",header=TRUE,row.names=1,check.names=FALSE,sep="\t")
#expr<-as.data.frame(t(expr))
#hist(rowSds(as.matrix(expr)),breaks=100,xlab="SD OF GENE EXPRESSION",
# main="Histogram of Standard Deviation in Gene Expression")
#expr<-expr[rowSds(as.matrix(expr))>0.4,]
expr[1:5,1:5]## TSPAN6 DPM1 SCYL3 C1orf112 FGR
## ID1 2.768135 2.773802 2.571244 2.129738 0.0000000
## ID3 2.685229 2.706376 2.341311 1.965268 0.8042363
## ID4 2.615901 2.674763 2.485935 2.133980 0.6303739
## ID6 2.530842 3.165768 2.256498 1.634036 0.7873765
## ID8 2.309199 2.574295 2.422172 1.855885 1.0770890dim(expr)## [1] 110 18023Now let us read the matrix of methylation levels and have a look at the data.
library("data.table")
meth<-suppressWarnings(as.data.frame(fread("Integr_Meth.txt")))
rownames(meth)<-meth$V1
meth$V1<-NULL
#meth<-as.data.frame(t(meth))
#hist(rowSds(as.matrix(meth)),breaks=100,xlab="SD OF METHYLATION",
# main="Histogram of Standard Deviation in Methylation")
#meth<-meth[rowSds(as.matrix(meth))>0.05,]
meth[1:5,1:5]## cg00000029 cg00000103 cg00000109 cg00000155 cg00000158
## ID1 0.8889442 0.9751705 1.137247 1.177708 1.0336774
## ID3 0.9016978 0.9840341 1.165657 1.180354 1.0069894
## ID4 0.8936279 0.9910230 1.155727 1.159165 0.9331931
## ID6 0.9557224 0.9558605 1.149778 1.193278 0.9260803
## ID8 0.9145566 0.9641449 1.167043 1.196637 0.9294772dim(meth)## [1] 110 816790Next, we will read the matrix of GWAS genetic variants:
gen<-read.delim("Integr_Gen.txt",header=TRUE,sep="\t",row.names=1,check.names=FALSE)
#gen<-as.data.frame(t(gen))
gen[1:5,1:5]## rs1851946_A rs2455144_A rs2455137_G rs2500278_G rs12031275_G
## ID1 0 0 0 0 2
## ID3 1 2 2 2 0
## ID4 2 0 0 0 2
## ID6 0 0 0 0 0
## ID8 2 1 1 1 0dim(gen)## [1] 110 2439And finally let us read phenotypic data:
phen<-read.delim("Integr_Phen.txt",header=TRUE,sep="\t",row.names=1,check.names=FALSE)
#phen<-as.data.frame(t(phen))
phen[1:4,1:4]## Age Sex BMI SI
## ID1 1.838849 1 1.409933 1.0253059
## ID3 1.662758 0 1.396199 0.6627578
## ID4 1.792392 0 1.457882 1.2013971
## ID6 1.832509 1 1.468347 0.4623980dim(phen)## [1] 110 4We will also read the vector of T2D status for the selected 110 individuals, we will use this for supervision of the DIABLO integration.
T2D<-read.delim("Integr_T2D.txt",header=TRUE,row.names=1,check.names=FALSE,sep="\t")
head(T2D)## T2D
## ID1 0
## ID3 0
## ID4 0
## ID6 0
## ID8 0
## ID10 0dim(T2D)## [1] 110 1It is useful to display the Venn Diagram of overlapping samples of the full OMICs data sets before doing integrative analysis:
library("VennDiagram")## Loading required package: grid## Loading required package: futile.loggerv<-venn.diagram(list(expr=rownames(expr), phen=rownames(phen), meth=rownames(meth), gen=rownames(gen)),fill = c("orange", "blue","red","green"),alpha = c(0.5, 0.5, 0.5, 0.5), cat.cex = 1.5, cex=1.5, filename=NULL)
grid.newpage()
grid.draw(v)
We can see that the overlap between all 4 OMICs is 110 samples.
DIABLO OMICS Integration
Now we will start integrating the three OMICs: 1) gene expression, 2) methylation and 3) clinical phenotypes. For this purpose we will concatenate gene expression, methylation and phenotype matrices into X matrix and use the T2D status as Y variable, so it is a typical Machine Learning setup: y=f(x), where x is the input, y is the class labels of individuals and the f-function is learnt from the data. We will be using DIABLO model from the mixOmics R packages (Kim-Anh Le Kao is the leader of the project), that is based on multi-block PLS model. To avoid the Curse of Dimensionality, we will pre-select features before integrating them. We build and train the integrative OMICs DIABLO model (as well as feature pre-selection) using train data set (80% of data) and make predictions on a test data set (20% of data).
k<-1
library("mixOmics")## Loading required package: MASS## Loading required package: lattice## Loading required package: ggplot2##
## Loaded mixOmics 6.8.5
## Thank you for using mixOmics!
## Tutorials: http://mixomics.org
## Bookdown vignette: https://mixomicsteam.github.io/Bookdown
## Questions, issues: Follow the prompts at http://mixomics.org/contact-us
## Cite us: citation('mixOmics')set.seed(k+100)
test_samples<-selected_ind[sample(1:length(selected_ind),round(length(selected_ind)*0.2))]
train_samples<-selected_ind[!selected_ind%in%test_samples]
Y.train<-as.factor(as.character(T2D[match(train_samples,rownames(T2D)),]))
Y.test<-as.factor(as.character(T2D[match(test_samples,rownames(T2D)),]))
X.train_expr<-expr[match(train_samples,rownames(expr)),]
X.test_expr<-expr[match(test_samples,rownames(expr)),]
expr_plsda<-plsda(X.train_expr, Y.train, ncomp=2)
features_expr1<-names(head(sort(abs(expr_plsda$loadings$X[,"comp1"]),decreasing=TRUE),50))
features_expr2<-names(head(sort(abs(expr_plsda$loadings$X[,"comp2"]),decreasing=TRUE),50))
X.train_expr_selected_features<-subset(X.train_expr,select=unique(c(features_expr1, features_expr2)))
X.test_expr_selected_features<-subset(X.test_expr,select=unique(c(features_expr1, features_expr2)))
X.train_meth<-meth[match(train_samples,rownames(meth)),]
X.test_meth<-meth[match(test_samples,rownames(meth)),]
meth_plsda<-plsda(X.train_meth, Y.train, ncomp=2)
features_meth1<-names(head(sort(abs(meth_plsda$loadings$X[,"comp1"]),decreasing=TRUE),50))
features_meth2<-names(head(sort(abs(meth_plsda$loadings$X[,"comp2"]),decreasing=TRUE),50))
X.train_meth_selected_features<-subset(X.train_meth,select=unique(c(features_meth1, features_meth2)))
X.test_meth_selected_features<-subset(X.test_meth,select=unique(c(features_meth1, features_meth2)))
X.train_gen<-gen[match(train_samples,rownames(gen)),]
X.test_gen<-gen[match(test_samples,rownames(gen)),]
gen_plsda<-plsda(X.train_gen, Y.train, ncomp=2)
features_gen1<-names(head(sort(abs(gen_plsda$loadings$X[,"comp1"]),decreasing=TRUE),20))
features_gen2<-names(head(sort(abs(gen_plsda$loadings$X[,"comp2"]),decreasing=TRUE),20))
X.train_gen_selected_features<-subset(X.train_gen,select=unique(c(features_gen1, features_gen2)))
X.test_gen_selected_features<-subset(X.test_gen,select=unique(c(features_gen1, features_gen2)))
X.train_phen<-phen[match(train_samples,rownames(phen)),]
X.test_phen<-phen[match(test_samples,rownames(phen)),]
data.train<-list(expr=X.train_expr_selected_features, meth=X.train_meth_selected_features,
gen=X.train_gen_selected_features, phen=X.train_phen)
design=matrix(0.1, ncol=length(data.train), nrow=length(data.train),
dimnames=list(names(data.train),names(data.train)))
diag(design)=0
design["expr","meth"]<-0.1
design["meth","expr"]<-0.1
design["meth","phen"]<-0.01
design["phen","meth"]<-0.01
design["expr","gen"]<-0.01
design["gen","expr"]<-0.01
design["meth","gen"]<-0.01
design["gen","meth"]<-0.01
ncomp=2
list.keepX = list("expr"=c(30,30), "meth"=c(30,30), "gen"=c(10,10), "phen"=c(4,4))
res = block.splsda(X=data.train,Y=Y.train,ncomp=ncomp,keepX=list.keepX,design=design,
scheme="horst",mode="regression",init="svd.single",near.zero.var=TRUE)## Design matrix has changed to include Y; each block will be
## linked to Y.plotIndiv(res,legend=TRUE,title="Human Pancreatic Islets: Individual Omics",ellipse=FALSE,ind.names=TRUE,cex=3)
plotArrow(res,ind.names=TRUE,legend=TRUE,title="Human Pancreatic Islets: Consensus Across Omics")
plotVar(res,var.names=TRUE,style='graphics',legend=TRUE,pch=c(16,17,18,19),cex=c(0.8,0.8,0.8,0.8),col=c('blue','red2',"darkgreen","cyan"))
circosPlot(res,cutoff=0.7,line=FALSE,size.variables=0.5)
cimDiablo(res,margins=c(11,18))
network(res,blocks=c(1,2),cex.node.name=0.6,color.node=c('blue','red2'),breaks=NULL)
network(res,blocks=c(1,3),cex.node.name=0.6,color.node=c('blue','darkgreen'),breaks=NULL)
network(res,blocks=c(1,4),cex.node.name=0.6,color.node=c('blue','cyan'),breaks=NULL)
network(res,blocks=c(2,3),cex.node.name=0.6,color.node=c('red2','darkgreen'),breaks=NULL)
network(res,blocks=c(2,4),cex.node.name=0.6,color.node=c('red2','cyan'),breaks=NULL)
network(res,blocks=c(3,4),cex.node.name=0.6,color.node=c('darkgreen','cyan'),breaks=NULL)
data.test<-list(expr=X.test_expr_selected_features, meth=X.test_meth_selected_features,
gen=X.test_gen_selected_features, phen=X.test_phen)
predict.diablo=predict(res, newdata=data.test, dist='centroids.dist')
print(data.frame(predict.diablo$class,Truth=Y.test))## centroids.dist.expr.comp1 centroids.dist.expr.comp2
## ID227 0 0
## ID184 0 0
## ID154 0 0
## ID168 1 1
## ID260 0 0
## ID186 0 0
## ID221 1 1
## ID196 0 0
## ID195 0 0
## ID189 0 0
## ID183 1 1
## ID4 0 0
## ID97 0 0
## ID21 0 0
## ID172 1 1
## ID91 0 0
## ID200 1 1
## ID176 1 1
## ID194 1 1
## ID163 0 0
## ID36 0 0
## ID241 1 1
## centroids.dist.meth.comp1 centroids.dist.meth.comp2
## ID227 0 0
## ID184 0 0
## ID154 0 0
## ID168 1 1
## ID260 0 0
## ID186 0 0
## ID221 1 1
## ID196 0 0
## ID195 0 0
## ID189 1 1
## ID183 1 1
## ID4 0 0
## ID97 0 0
## ID21 0 0
## ID172 1 1
## ID91 0 0
## ID200 1 1
## ID176 1 0
## ID194 1 1
## ID163 0 0
## ID36 0 0
## ID241 1 1
## centroids.dist.gen.comp1 centroids.dist.gen.comp2
## ID227 0 0
## ID184 1 1
## ID154 1 1
## ID168 0 0
## ID260 0 0
## ID186 1 1
## ID221 0 0
## ID196 0 1
## ID195 0 0
## ID189 0 0
## ID183 0 0
## ID4 0 0
## ID97 0 0
## ID21 0 0
## ID172 0 0
## ID91 1 1
## ID200 0 1
## ID176 0 0
## ID194 0 1
## ID163 0 1
## ID36 0 1
## ID241 0 1
## centroids.dist.phen.comp1 centroids.dist.phen.comp2 Truth
## ID227 0 0 0
## ID184 0 0 0
## ID154 1 1 0
## ID168 1 1 1
## ID260 0 0 0
## ID186 0 0 0
## ID221 1 1 1
## ID196 0 0 0
## ID195 0 1 0
## ID189 1 1 0
## ID183 0 0 1
## ID4 0 0 0
## ID97 1 1 0
## ID21 0 0 0
## ID172 0 0 1
## ID91 1 1 1
## ID200 1 1 1
## ID176 1 0 0
## ID194 0 0 1
## ID163 0 0 0
## ID36 1 1 0
## ID241 1 1 1The network, circus and arrow plots provide an interpretation of the integrative model, i.e. we can see the linkage between the features across the 4 OMICs and potentially can understand the biological interplay between the different layers of information. Let us now display what the integrative model classifier has learnt and let us see how it can classify the new data points from the test data set.
df1<-data.frame(expr=res$variates$expr[,"comp1"],meth=res$variates$meth[,"comp1"],gen=res$variates$gen[,"comp1"],phen=res$variates$phen[,"comp1"])
av1<-rowMeans(df1)
df2<-data.frame(expr=res$variates$expr[,"comp2"],meth=res$variates$meth[,"comp2"],gen=res$variates$gen[,"comp2"],phen=res$variates$phen[,"comp2"])
av2<-rowMeans(df2)
train_df<-data.frame(x=as.numeric(av1),y=as.numeric(av2),label=Y.train)
train_df$color<-ifelse(train_df$label==0,"blue","red")
plot(train_df$x,train_df$y,col=train_df$color,xlab="PLS LATENT DIMENSION 1",ylab="PLS LATENT DIMENSION 2")
legend("topleft", inset=.02, c("Diabetics","Non-Diabetics"), fill=c("red","blue"))
train_df$color<-NULL
mdl <- glm(as.factor(label)~ ., data=train_df, family=binomial)
slope <- coef(mdl)[2]/(-coef(mdl)[3])
intercept <- coef(mdl)[1]/(-coef(mdl)[3])
abline(intercept, slope, col="darkorange", lwd=2)
df1pred<-data.frame(expr=predict.diablo$variates$expr[,"dim1"],meth=predict.diablo$variates$meth[,"dim1"],gen=predict.diablo$variates$gen[,"dim1"],phen=predict.diablo$variates$phen[,"dim1"])
av1pred<-rowMeans(df1pred)
df2pred<-data.frame(expr=predict.diablo$variates$expr[,"dim2"],meth=predict.diablo$variates$meth[,"dim2"],gen=predict.diablo$variates$gen[,"dim2"],phen=predict.diablo$variates$phen[,"dim2"])
av2pred<-rowMeans(df2pred)
test_df<-data.frame(x=as.numeric(av1pred),y=as.numeric(av2pred),label=Y.test)
test_df$color<-ifelse(test_df$label==0,"blue","red")
points(test_df$x,test_df$y,col=test_df$color,pch=19)
Now let us calculate some prediction metrics such as the accuracy of prediction, meaning the fraction of times we predict the T2D status correctly:
DIABLO_predict1<-predict.diablo$MajorityVote$centroids.dist[,1]
if(any(is.na(DIABLO_predict1))==TRUE)
{
failed_samples1<-names(DIABLO_predict1)[is.na(DIABLO_predict1)==TRUE]
for(s1 in failed_samples1)
{
if(as.numeric(predict.diablo$class$centroids.dist$expr[,1][s1])==as.numeric(predict.diablo$class$centroids.dist$meth[,1][s1]))
{
DIABLO_predict1[s1]<-predict.diablo$class$centroids.dist$expr[,1][s1]
}
}
}
conf_matrix_comp1<-table(DIABLO_predict1,Y.test)
print(conf_matrix_comp1)## Y.test
## DIABLO_predict1 0 1
## 0 12 1
## 1 1 7acc1<-round((sum(diag(conf_matrix_comp1))/sum(conf_matrix_comp1))*100)
print(paste0("Classification Accuracy from DIABLO Component 1: ", acc1))## [1] "Classification Accuracy from DIABLO Component 1: 90"DIABLO_predict2<-predict.diablo$MajorityVote$centroids.dist[,2]
if(any(is.na(DIABLO_predict2))==TRUE)
{
failed_samples2<-names(DIABLO_predict2)[is.na(DIABLO_predict2)==TRUE]
for(s2 in failed_samples2)
{
if(as.numeric(predict.diablo$class$centroids.dist$expr[,2][s2])==as.numeric(predict.diablo$class$centroids.dist$meth[,2][s2]))
{
DIABLO_predict2[s2]<-predict.diablo$class$centroids.dist$expr[,2][s2]
}
}
}
conf_matrix_comp2<-table(DIABLO_predict2,Y.test)
print(conf_matrix_comp2)## Y.test
## DIABLO_predict2 0 1
## 0 13 1
## 1 0 7acc2<-round((sum(diag(conf_matrix_comp2))/sum(conf_matrix_comp2))*100)
print(paste0("Classification Accuracy from DIABLO Component 2: ", acc2))## [1] "Classification Accuracy from DIABLO Component 2: 95"We can see that the accuracy of prediction is very high, however, since our data set is unbalanced, it is not a very good idea to use accuracy as an ultimate metric of model evaluation. Therefore, let us plot the ROC curve of DIABLO prediction and compare predictions from DIABLO component 1 and component 2:
library("ROCit")
DIABLO_predict1_expr<-predict.diablo$predict$expr[,,1][,2]
DIABLO_predict1_meth<-predict.diablo$predict$meth[,,1][,2]
DIABLO_predict1_gen<-predict.diablo$predict$gen[,,1][,2]
DIABLO_predict1_phen<-predict.diablo$predict$phen[,,1][,2]
DIABLO_predict1_score<-rowMeans(data.frame(DIABLO_predict1_expr,DIABLO_predict1_meth,DIABLO_predict1_gen,DIABLO_predict1_phen))
roc_obj1<-rocit(as.numeric(DIABLO_predict1_score),as.numeric(as.character(Y.test)))
roc_obj1## $method
## [1] "empirical"
##
## $pos_count
## [1] 8
##
## $neg_count
## [1] 14
##
## $pos_D
## [1] 0.6479727 0.5935829 0.5256018 0.4474015 0.3729831 0.3674957 0.3465465
## [8] 0.3152495
##
## $neg_D
## [1] 0.45147708 0.39295108 0.31508390 0.28150240 0.23641488
## [6] 0.20794347 0.20353990 0.15932217 0.11597300 0.11514357
## [11] 0.10850999 0.07914260 0.02925979 -0.04470402
##
## $AUC
## [1] 0.9196429
##
## $Cutoff
## [1] Inf 0.64797269 0.59358288 0.52560184 0.45147708
## [6] 0.44740147 0.39295108 0.37298305 0.36749568 0.34654647
## [11] 0.31524947 0.31508390 0.28150240 0.23641488 0.20794347
## [16] 0.20353990 0.15932217 0.11597300 0.11514357 0.10850999
## [21] 0.07914260 0.02925979 -0.04470402
##
## $TPR
## [1] 0.000 0.125 0.250 0.375 0.375 0.500 0.500 0.625 0.750 0.875 1.000
## [12] 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000
## [23] 1.000
##
## $FPR
## [1] 0.00000000 0.00000000 0.00000000 0.00000000 0.07142857 0.07142857
## [7] 0.14285714 0.14285714 0.14285714 0.14285714 0.14285714 0.21428571
## [13] 0.28571429 0.35714286 0.42857143 0.50000000 0.57142857 0.64285714
## [19] 0.71428571 0.78571429 0.85714286 0.92857143 1.00000000
##
## attr(,"class")
## [1] "rocit"my_auc1<-0.07142857*0.375+0.07142857*0.5+(1-0.14285714)*1
my_auc1## [1] 0.9196429plot(roc_obj1$FPR,roc_obj1$TPR,col="red",type="o",ylab="SENSITIVITY (TPR)",xlab="1-SPECIFISITY (FPR)",pch=19)
DIABLO_predict1_integr<-data.frame(DIABLO_predict1_score,DIABLO_predict1_expr,DIABLO_predict1_meth,DIABLO_predict1_gen,DIABLO_predict1_phen,Y.test)
DIABLO_predict1_integr<-DIABLO_predict1_integr[order(-as.numeric(DIABLO_predict1_integr$DIABLO_predict1_score)),]
DIABLO_predict1_integr## DIABLO_predict1_score DIABLO_predict1_expr DIABLO_predict1_meth
## ID200 0.64797269 0.937229783 0.92625879
## ID241 0.59358288 0.653102558 0.81750702
## ID194 0.52560184 0.940421998 0.91060590
## ID176 0.45147708 0.758619817 0.63214077
## ID221 0.44740147 0.578236135 0.65816982
## ID189 0.39295108 0.295121999 0.41269325
## ID168 0.37298305 0.488454189 0.54610304
## ID172 0.36749568 0.710968381 0.44252173
## ID183 0.34654647 0.462599661 0.81986956
## ID91 0.31524947 0.237028387 0.19752766
## ID195 0.31508390 0.380268128 0.30228998
## ID97 0.28150240 0.299570425 0.10517239
## ID154 0.23641488 0.303139657 -0.23289343
## ID196 0.20794347 0.353002091 0.15989229
## ID163 0.20353990 0.197997266 0.03024688
## ID186 0.15932217 0.004421755 0.02623801
## ID184 0.11597300 0.068639148 -0.12447298
## ID227 0.11514357 0.004404258 0.02948682
## ID36 0.10850999 -0.168147125 0.10124112
## ID21 0.07914260 0.145430950 0.01945029
## ID4 0.02925979 -0.276663814 -0.20323961
## ID260 -0.04470402 -0.130024383 -0.20710691
## DIABLO_predict1_gen DIABLO_predict1_phen Y.test
## ID200 0.20497709 0.52342511 1
## ID241 0.35154259 0.55217936 1
## ID194 0.14132158 0.11005788 1
## ID176 0.10239033 0.31275741 0
## ID221 0.23679453 0.31640538 1
## ID189 0.26749585 0.59649320 0
## ID168 -0.07061965 0.52799463 1
## ID172 0.13818259 0.17831003 1
## ID183 -0.16279651 0.26651315 1
## ID91 0.47005831 0.35638351 1
## ID195 0.30309411 0.27468339 0
## ID97 0.02156155 0.69970523 0
## ID154 0.55988327 0.31553002 0
## ID196 0.30309411 0.01578537 0
## ID163 0.31952207 0.26639340 0
## ID186 0.51956385 0.08706507 0
## ID184 0.42158322 0.09814259 0
## ID227 0.27088340 0.15579979 0
## ID36 0.12108472 0.37986123 0
## ID21 -0.02838194 0.18007112 0
## ID4 0.35243248 0.24451012 0
## ID260 -0.01652360 0.17483882 0DIABLO_predict2_expr<-predict.diablo$predict$expr[,,2][,2]
DIABLO_predict2_meth<-predict.diablo$predict$meth[,,2][,2]
DIABLO_predict2_gen<-predict.diablo$predict$gen[,,2][,2]
DIABLO_predict2_phen<-predict.diablo$predict$phen[,,2][,2]
DIABLO_predict2_score<-rowMeans(data.frame(DIABLO_predict2_expr,DIABLO_predict2_meth,DIABLO_predict2_gen,DIABLO_predict2_phen))
roc_obj2<-rocit(as.numeric(DIABLO_predict2_score),as.numeric(as.character(Y.test)))
roc_obj2## $method
## [1] "empirical"
##
## $pos_count
## [1] 8
##
## $neg_count
## [1] 14
##
## $pos_D
## [1] 0.7419619 0.6916058 0.6058110 0.5509729 0.5275448 0.4318585 0.3958000
## [8] 0.3845158
##
## $neg_D
## [1] 0.41637059 0.29193374 0.28469600 0.28224560 0.26100506
## [6] 0.25245874 0.17802293 0.16880295 0.13863866 0.13169311
## [11] 0.09658062 0.08460397 0.07265228 -0.02844850
##
## $AUC
## [1] 0.9821429
##
## $Cutoff
## [1] Inf 0.74196194 0.69160576 0.60581099 0.55097286
## [6] 0.52754482 0.43185855 0.41637059 0.39579997 0.38451575
## [11] 0.29193374 0.28469600 0.28224560 0.26100506 0.25245874
## [16] 0.17802293 0.16880295 0.13863866 0.13169311 0.09658062
## [21] 0.08460397 0.07265228 -0.02844850
##
## $TPR
## [1] 0.000 0.125 0.250 0.375 0.500 0.625 0.750 0.750 0.875 1.000 1.000
## [12] 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000
## [23] 1.000
##
## $FPR
## [1] 0.00000000 0.00000000 0.00000000 0.00000000 0.00000000 0.00000000
## [7] 0.00000000 0.07142857 0.07142857 0.07142857 0.14285714 0.21428571
## [13] 0.28571429 0.35714286 0.42857143 0.50000000 0.57142857 0.64285714
## [19] 0.71428571 0.78571429 0.85714286 0.92857143 1.00000000
##
## attr(,"class")
## [1] "rocit"lines(roc_obj2$FPR,roc_obj2$TPR,col="blue",type="o",pch=19)
lines(c(0,1),c(0,1),col="black")
legend("bottomright",legend=c(paste0("DIABLO COMP1 AUC = ",round(roc_obj1$AUC,2)),paste0("DIABLO COMP2 AUC = ",round(roc_obj2$AUC,2))),col=c("red","blue"),inset=0.02,lty=c(1,1))
DIABLO_predict2_integr<-data.frame(DIABLO_predict2_score,DIABLO_predict2_expr,DIABLO_predict2_meth,DIABLO_predict2_gen,DIABLO_predict2_phen,Y.test)
DIABLO_predict2_integr<-DIABLO_predict2_integr[order(-as.numeric(DIABLO_predict2_integr$DIABLO_predict2_score)),]
DIABLO_predict2_integr## DIABLO_predict2_score DIABLO_predict2_expr DIABLO_predict2_meth
## ID200 0.74196194 0.90417965 0.95870973
## ID241 0.69160576 0.86384459 0.87983602
## ID194 0.60581099 1.01220204 0.83748293
## ID221 0.55097286 0.81337243 0.74866557
## ID183 0.52754482 0.85141700 1.04077989
## ID168 0.43185855 0.65705394 0.61925401
## ID189 0.41637059 0.37334054 0.42991535
## ID91 0.39579997 0.40190775 0.33179793
## ID172 0.38451575 0.66021751 0.52546480
## ID97 0.29193374 0.35992054 0.18931742
## ID195 0.28469600 0.34238926 0.14209602
## ID176 0.28224560 0.46175851 0.38959111
## ID154 0.26100506 0.19564166 -0.15740883
## ID36 0.25245874 -0.01614756 0.15328729
## ID186 0.17802293 0.03284843 0.10628508
## ID227 0.16880295 0.08844496 0.04665079
## ID196 0.13863866 0.07165567 0.01971821
## ID163 0.13169311 -0.04228179 -0.11842152
## ID184 0.09658062 -0.01757638 -0.16783628
## ID21 0.08460397 -0.01362324 0.05399999
## ID260 0.07265228 -0.09813842 -0.08621858
## ID4 -0.02844850 -0.27447487 -0.21588235
## DIABLO_predict2_gen DIABLO_predict2_phen Y.test
## ID200 0.56413495 0.54082341 1
## ID241 0.47192848 0.55081394 1
## ID194 0.47205193 0.10150708 1
## ID221 0.29472760 0.34712584 1
## ID183 -0.06671858 0.28470098 1
## ID168 -0.08864359 0.53976982 1
## ID189 0.25478684 0.60743965 0
## ID91 0.46909908 0.38039514 1
## ID172 0.22068688 0.13169380 1
## ID97 -0.06542497 0.68392198 0
## ID195 0.34848704 0.30581168 0
## ID176 -0.01269149 0.29032429 0
## ID154 0.67925272 0.32653470 0
## ID36 0.47104598 0.40164926 0
## ID186 0.49086806 0.08209016 0
## ID227 0.35100936 0.18910668 0
## ID196 0.41771880 0.04546197 0
## ID163 0.42625542 0.26122034 0
## ID184 0.48631633 0.08541879 0
## ID21 0.12005511 0.17798404 0
## ID260 0.31733767 0.15762844 0
## ID4 0.13276606 0.24379718 0#roc_obj<-rocit(as.numeric(DIABLO_predict1),as.numeric(as.character(Y.test)))
#plot(roc_obj$FPR,roc_obj$TPR,col="red",type="o",ylab="SENSITIVITY (TPR)",xlab="1-SPECIFISITY (FPR)")
#lines(c(0,1),c(0,1),col="black")
#roc_obj_expr<-rocit(as.numeric(DIABLO_predict1_expr),as.numeric(as.character(Y.test)))
#lines(roc_obj_expr$FPR,roc_obj_expr$TPR,col="blue",type="o")
#roc_obj_meth<-rocit(as.numeric(DIABLO_predict1_meth),as.numeric(as.character(Y.test)))
#lines(roc_obj_meth$FPR,roc_obj_meth$TPR,col="green",type="o")
#roc_obj_gen<-rocit(as.numeric(DIABLO_predict1_gen),as.numeric(as.character(Y.test)))
#lines(roc_obj_gen$FPR,roc_obj_gen$TPR,col="magenta",type="o")
#roc_obj_phen<-rocit(as.numeric(DIABLO_predict1_phen),as.numeric(as.character(Y.test)))
#lines(roc_obj_phen$FPR,roc_obj_phen$TPR,col="cyan",type="o")
#legend("bottomright",legend=c("DIABLO","EXPR","METH","GEN","PHEN"),col=c("red","blue","green","magenta","cyan"),
# inset=0.02,lty=c(1,1,1,1,1))We conclude that DIABLO component 2 is more predictive than component 1, that is also confirmed by the higher accuracy of T2D vs. NonT2D classification. The training and evaluation of the model has been performed on one train-test split (so-called holdd-out cross-validartion). Now we are going to do this split multiple times and average the prediction metrics such as accuracy and ROC-curve. In this way we will build confidence intervals for the T2D status prediction.
Building Confidence Intervals for DIABLO Integrative Model
Here we are going to build a loop where we split the 110 individuals into train and test set multiple times (hold-out cross-vlaidation in Machine Learning terminology). Within each split we will run an sPLS-DA model for each OMIC on the train data set only and use the pre-selected features for integrating the 4 OMICs with DIABLO. The results of the integration will be validated multiple times on the test data set in terms of the accuracy of the prediction. In this way we will build confidence intervals for the accuracy of prediction and ROC curve of prediction.
N_repeat<-100
library("mixOmics")
library("ROCit")
library("matrixStats")
comp1_auc<-vector()
comp1_tpr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_fpr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_auc_expr<-vector()
comp1_tpr_expr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_fpr_expr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_auc_meth<-vector()
comp1_tpr_meth<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_fpr_meth<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_auc_gen<-vector()
comp1_tpr_gen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_fpr_gen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_auc_phen<-vector()
comp1_tpr_phen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_fpr_phen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_auc<-vector()
comp2_tpr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_fpr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_auc_expr<-vector()
comp2_tpr_expr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_fpr_expr<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_auc_meth<-vector()
comp2_tpr_meth<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_fpr_meth<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_auc_gen<-vector()
comp2_tpr_gen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_fpr_gen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_auc_phen<-vector()
comp2_tpr_phen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp2_fpr_phen<-matrix(NA,ncol=length(test_samples)+1,nrow=N_repeat)
comp1_acc<-vector(); comp2_acc<-vector()
for(k in 1:N_repeat)
{
print(paste0("Working with split No.", k))
gc()
set.seed(k+100)
test_samples<-selected_ind[sample(1:length(selected_ind),round(length(selected_ind)*0.2))]
train_samples<-selected_ind[!selected_ind%in%test_samples]
Y.train<-as.factor(as.character(T2D[match(train_samples,rownames(T2D)),]))
Y.test<-as.factor(as.character(T2D[match(test_samples,rownames(T2D)),]))
X.train_expr<-expr[match(train_samples,rownames(expr)),]
X.test_expr<-expr[match(test_samples,rownames(expr)),]
expr_plsda<-plsda(X.train_expr, Y.train, ncomp=2)
features_expr1<-names(head(sort(abs(expr_plsda$loadings$X[,"comp1"]),decreasing=TRUE),50))
features_expr2<-names(head(sort(abs(expr_plsda$loadings$X[,"comp2"]),decreasing=TRUE),50))
X.train_expr_selected_features<-subset(X.train_expr,select=unique(c(features_expr1, features_expr2)))
X.test_expr_selected_features<-subset(X.test_expr,select=unique(c(features_expr1, features_expr2)))
X.train_meth<-meth[match(train_samples,rownames(meth)),]
X.test_meth<-meth[match(test_samples,rownames(meth)),]
meth_plsda<-plsda(X.train_meth, Y.train, ncomp=2)
features_meth1<-names(head(sort(abs(meth_plsda$loadings$X[,"comp1"]),decreasing=TRUE),50))
features_meth2<-names(head(sort(abs(meth_plsda$loadings$X[,"comp2"]),decreasing=TRUE),50))
X.train_meth_selected_features<-subset(X.train_meth,select=unique(c(features_meth1, features_meth2)))
X.test_meth_selected_features<-subset(X.test_meth,select=unique(c(features_meth1, features_meth2)))
X.train_gen<-gen[match(train_samples,rownames(gen)),]
X.test_gen<-gen[match(test_samples,rownames(gen)),]
gen_plsda<-plsda(X.train_gen, Y.train, ncomp=2)
features_gen1<-names(head(sort(abs(gen_plsda$loadings$X[,"comp1"]),decreasing=TRUE),20))
features_gen2<-names(head(sort(abs(gen_plsda$loadings$X[,"comp2"]),decreasing=TRUE),20))
X.train_gen_selected_features<-subset(X.train_gen,select=unique(c(features_gen1, features_gen2)))
X.test_gen_selected_features<-subset(X.test_gen,select=unique(c(features_gen1, features_gen2)))
X.train_phen<-phen[match(train_samples,rownames(phen)),]
X.test_phen<-phen[match(test_samples,rownames(phen)),]
data.train<-list(expr=X.train_expr_selected_features, meth=X.train_meth_selected_features,
gen=X.train_gen_selected_features, phen=X.train_phen)
design=matrix(0.1, ncol=length(data.train), nrow=length(data.train),
dimnames=list(names(data.train),names(data.train)))
diag(design)=0
design["expr","meth"]<-0.1
design["meth","expr"]<-0.1
design["meth","phen"]<-0.01
design["phen","meth"]<-0.01
design["expr","gen"]<-0.01
design["gen","expr"]<-0.01
design["meth","gen"]<-0.01
design["gen","meth"]<-0.01
ncomp=2
list.keepX = list("expr"=c(30,30), "meth"=c(30,30), "gen"=c(5,5), "phen"=c(4,4))
#tune = tune.block.splsda(X=data.train,Y=Y.train,ncomp=ncomp,test.keepX=list.keepX,design=design,nrepeat=3,folds=2)
res = block.splsda(X=data.train,Y=Y.train,ncomp=ncomp,keepX=list.keepX,design=design,
scheme="horst",mode="regression",init="svd.single",near.zero.var=TRUE)
data.test<-list(expr=X.test_expr_selected_features, meth=X.test_meth_selected_features,
gen=X.test_gen_selected_features, phen=X.test_phen)
predict.diablo=predict(res, newdata=data.test, dist='centroids.dist')
#print(data.frame(predict.diablo$class,Truth=Y.test))
DIABLO_predict1_expr<-predict.diablo$predict$expr[,,1][,2]
DIABLO_predict1_meth<-predict.diablo$predict$meth[,,1][,2]
DIABLO_predict1_gen<-predict.diablo$predict$gen[,,1][,2]
DIABLO_predict1_phen<-predict.diablo$predict$phen[,,1][,2]
DIABLO_predict1_score<-rowWeightedMeans(as.matrix(data.frame(DIABLO_predict1_expr,DIABLO_predict1_meth,
DIABLO_predict1_gen,DIABLO_predict1_phen)),w=c(1,0.8,0.1,0.1))
names(DIABLO_predict1_score)<-names(DIABLO_predict1_expr)
DIABLO_predict1<-predict.diablo$MajorityVote$centroids.dist[,1]
if(any(is.na(DIABLO_predict1))==TRUE)
{
failed_samples1<-names(DIABLO_predict1)[is.na(DIABLO_predict1)==TRUE]
for(s1 in failed_samples1)
{
if(as.numeric(predict.diablo$class$centroids.dist$expr[,1][s1])==as.numeric(predict.diablo$class$centroids.dist$meth[,1][s1]))
{
DIABLO_predict1[s1]<-predict.diablo$class$centroids.dist$expr[,1][s1]
}
DIABLO_predict1_score[s1]<-predict.diablo$predict$expr[,,1][,2][s1]
}
#DIABLO_predict1[failed_samples1]<-predict.diablo$class$centroids.dist$expr[,1][failed_samples1]
}
conf_matrix_comp1<-table(DIABLO_predict1,Y.test)
print(conf_matrix_comp1)
acc1<-round((sum(diag(conf_matrix_comp1))/sum(conf_matrix_comp1))*100)
comp1_acc<-append(comp1_acc,acc1)
print(paste0("Classification Accuracy from PLS Component 1: ", acc1))
roc_obj1<-rocit(as.numeric(DIABLO_predict1_score),as.numeric(as.character(Y.test)))
roc_obj1_expr<-rocit(as.numeric(DIABLO_predict1_expr),as.numeric(as.character(Y.test)))
roc_obj1_meth<-rocit(as.numeric(DIABLO_predict1_meth),as.numeric(as.character(Y.test)))
roc_obj1_gen<-rocit(as.numeric(DIABLO_predict1_gen),as.numeric(as.character(Y.test)))
roc_obj1_phen<-rocit(as.numeric(DIABLO_predict1_phen),as.numeric(as.character(Y.test)))
comp1_auc<-append(comp1_auc,roc_obj1$AUC)
comp1_auc_expr<-append(comp1_auc_expr,roc_obj1_expr$AUC)
comp1_auc_meth<-append(comp1_auc_meth,roc_obj1_meth$AUC)
comp1_auc_gen<-append(comp1_auc_gen,roc_obj1_gen$AUC)
comp1_auc_phen<-append(comp1_auc_phen,roc_obj1_phen$AUC)
print(paste0("Classification ROC AUC from DIABLO Component 1: ", roc_obj1$AUC))
print(paste0("Classification ROC AUC from Expression Component 1: ", roc_obj1_expr$AUC))
print(paste0("Classification ROC AUC from Methylation Component 1: ", roc_obj1_meth$AUC))
print(paste0("Classification ROC AUC from Genotype Component 1: ", roc_obj1_gen$AUC))
print(paste0("Classification ROC AUC from Phenotype Component 1: ", roc_obj1_phen$AUC))
comp1_tpr[k,]<-roc_obj1$TPR
comp1_fpr[k,]<-roc_obj1$FPR
comp1_tpr_expr[k,]<-roc_obj1_expr$TPR
comp1_fpr_expr[k,]<-roc_obj1_expr$FPR
comp1_tpr_meth[k,]<-roc_obj1_meth$TPR
comp1_fpr_meth[k,]<-roc_obj1_meth$FPR
comp1_tpr_gen[k,]<-roc_obj1_gen$TPR
comp1_fpr_gen[k,]<-roc_obj1_gen$FPR
comp1_tpr_phen[k,]<-roc_obj1_phen$TPR
comp1_fpr_phen[k,]<-roc_obj1_phen$FPR
DIABLO_predict2_expr<-predict.diablo$predict$expr[,,2][,2]
DIABLO_predict2_meth<-predict.diablo$predict$meth[,,2][,2]
DIABLO_predict2_gen<-predict.diablo$predict$gen[,,2][,2]
DIABLO_predict2_phen<-predict.diablo$predict$phen[,,2][,2]
DIABLO_predict2_score<-rowWeightedMeans(as.matrix(data.frame(DIABLO_predict2_expr,DIABLO_predict2_meth,
DIABLO_predict2_gen,DIABLO_predict2_phen)),w=c(1,0.8,0.1,0.1))
names(DIABLO_predict2_score)<-names(DIABLO_predict2_expr)
DIABLO_predict2<-predict.diablo$MajorityVote$centroids.dist[,2]
if(any(is.na(DIABLO_predict2))==TRUE)
{
failed_samples2<-names(DIABLO_predict2)[is.na(DIABLO_predict2)==TRUE]
for(s2 in failed_samples2)
{
if(as.numeric(predict.diablo$class$centroids.dist$expr[,2][s2])==as.numeric(predict.diablo$class$centroids.dist$meth[,2][s2]))
{
DIABLO_predict2[s2]<-predict.diablo$class$centroids.dist$expr[,2][s2]
}
DIABLO_predict2_score[s2]<-predict.diablo$predict$expr[,,2][,2][s2]
}
#DIABLO_predict2[failed_samples2]<-predict.diablo$class$centroids.dist$expr[,2][failed_samples2]
}
conf_matrix_comp2<-table(DIABLO_predict2,Y.test)
print(conf_matrix_comp2)
acc2<-round((sum(diag(conf_matrix_comp2))/sum(conf_matrix_comp2))*100)
comp2_acc<-append(comp2_acc,acc2)
print(paste0("Classification Accuracy from PLS Component 2: ", acc2))
roc_obj2<-rocit(as.numeric(DIABLO_predict2_score),as.numeric(as.character(Y.test)))
roc_obj2_expr<-rocit(as.numeric(DIABLO_predict2_expr),as.numeric(as.character(Y.test)))
roc_obj2_meth<-rocit(as.numeric(DIABLO_predict2_meth),as.numeric(as.character(Y.test)))
roc_obj2_gen<-rocit(as.numeric(DIABLO_predict2_gen),as.numeric(as.character(Y.test)))
roc_obj2_phen<-rocit(as.numeric(DIABLO_predict2_phen),as.numeric(as.character(Y.test)))
comp2_auc<-append(comp2_auc,roc_obj2$AUC)
comp2_auc_expr<-append(comp2_auc_expr,roc_obj2_expr$AUC)
comp2_auc_meth<-append(comp2_auc_meth,roc_obj2_meth$AUC)
comp2_auc_gen<-append(comp2_auc_gen,roc_obj2_gen$AUC)
comp2_auc_phen<-append(comp2_auc_phen,roc_obj2_phen$AUC)
print(paste0("Classification ROC AUC from DIABLO Component 2: ", roc_obj2$AUC))
print(paste0("Classification ROC AUC from Expression Component 2: ", roc_obj2_expr$AUC))
print(paste0("Classification ROC AUC from Methylation Component 2: ", roc_obj2_meth$AUC))
print(paste0("Classification ROC AUC from Genotype Component 2: ", roc_obj2_gen$AUC))
print(paste0("Classification ROC AUC from Phenotype Component 2: ", roc_obj2_phen$AUC))
comp2_tpr[k,]<-roc_obj2$TPR
comp2_fpr[k,]<-roc_obj2$FPR
comp2_tpr_expr[k,]<-roc_obj2_expr$TPR
comp2_fpr_expr[k,]<-roc_obj2_expr$FPR
comp2_tpr_meth[k,]<-roc_obj2_meth$TPR
comp2_fpr_meth[k,]<-roc_obj2_meth$FPR
comp2_tpr_gen[k,]<-roc_obj2_gen$TPR
comp2_fpr_gen[k,]<-roc_obj2_gen$FPR
comp2_tpr_phen[k,]<-roc_obj2_phen$TPR
comp2_fpr_phen[k,]<-roc_obj2_phen$FPR
print("***********************************************************")
}## [1] "Working with split No.1"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 1
## 1 1 7
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.928571428571429"
## [1] "Classification ROC AUC from Expression Component 1: 0.901785714285714"
## [1] "Classification ROC AUC from Methylation Component 1: 0.955357142857143"
## [1] "Classification ROC AUC from Genotype Component 1: 0.473214285714286"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.642857142857143"
## Y.test
## DIABLO_predict2 0 1
## 0 13 1
## 1 0 7
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.991071428571429"
## [1] "Classification ROC AUC from Methylation Component 2: 0.982142857142857"
## [1] "Classification ROC AUC from Genotype Component 2: 0.526785714285714"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.642857142857143"
## [1] "***********************************************************"
## [1] "Working with split No.2"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 3
## 1 1 3
## [1] "Classification Accuracy from PLS Component 1: 81"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.885416666666667"
## [1] "Classification ROC AUC from Expression Component 1: 0.895833333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.458333333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.708333333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 15 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.947916666666667"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.791666666666667"
## [1] "Classification ROC AUC from Genotype Component 2: 0.4375"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.729166666666667"
## [1] "***********************************************************"
## [1] "Working with split No.3"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 0 4
## [1] "Classification Accuracy from PLS Component 1: 89"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.888888888888889"
## [1] "Classification ROC AUC from Expression Component 1: 0.948717948717949"
## [1] "Classification ROC AUC from Methylation Component 1: 0.811965811965812"
## [1] "Classification ROC AUC from Genotype Component 1: 0.487179487179487"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.452991452991453"
## Y.test
## DIABLO_predict2 0 1
## 0 12 3
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.957264957264957"
## [1] "Classification ROC AUC from Expression Component 2: 0.982905982905983"
## [1] "Classification ROC AUC from Methylation Component 2: 0.88034188034188"
## [1] "Classification ROC AUC from Genotype Component 2: 0.478632478632479"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.461538461538462"
## [1] "***********************************************************"
## [1] "Working with split No.4"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 2
## 1 2 3
## [1] "Classification Accuracy from PLS Component 1: 82"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.905882352941176"
## [1] "Classification ROC AUC from Expression Component 1: 0.917647058823529"
## [1] "Classification ROC AUC from Methylation Component 1: 0.858823529411765"
## [1] "Classification ROC AUC from Genotype Component 1: 0.388235294117647"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.470588235294118"
## Y.test
## DIABLO_predict2 0 1
## 0 15 3
## 1 1 2
## [1] "Classification Accuracy from PLS Component 2: 81"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.905882352941176"
## [1] "Classification ROC AUC from Expression Component 2: 0.894117647058824"
## [1] "Classification ROC AUC from Methylation Component 2: 0.917647058823529"
## [1] "Classification ROC AUC from Genotype Component 2: 0.435294117647059"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.470588235294118"
## [1] "***********************************************************"
## [1] "Working with split No.5"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 3 4
## [1] "Classification Accuracy from PLS Component 1: 76"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.864583333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.833333333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 0.947916666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.479166666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.625"
## Y.test
## DIABLO_predict2 0 1
## 0 12 2
## 1 1 3
## [1] "Classification Accuracy from PLS Component 2: 83"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.895833333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.833333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.864583333333333"
## [1] "Classification ROC AUC from Genotype Component 2: 0.645833333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.59375"
## [1] "***********************************************************"
## [1] "Working with split No.6"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 3
## 1 0 4
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.948717948717949"
## [1] "Classification ROC AUC from Expression Component 1: 0.871794871794872"
## [1] "Classification ROC AUC from Methylation Component 1: 0.923076923076923"
## [1] "Classification ROC AUC from Genotype Component 1: 0.521367521367521"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.487179487179487"
## Y.test
## DIABLO_predict2 0 1
## 0 13 3
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.931623931623932"
## [1] "Classification ROC AUC from Expression Component 2: 0.905982905982906"
## [1] "Classification ROC AUC from Methylation Component 2: 0.863247863247863"
## [1] "Classification ROC AUC from Genotype Component 2: 0.504273504273504"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.504273504273504"
## [1] "***********************************************************"
## [1] "Working with split No.7"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 1
## 1 2 3
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 0.930555555555556"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.361111111111111"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.541666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 16 0
## 1 1 4
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.986111111111111"
## [1] "Classification ROC AUC from Expression Component 2: 0.986111111111111"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.236111111111111"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.541666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.8"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 1
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 89"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Expression Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Methylation Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Genotype Component 1: 0.628571428571429"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.6"
## Y.test
## DIABLO_predict2 0 1
## 0 12 2
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Expression Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Methylation Component 2: 0.952380952380952"
## [1] "Classification ROC AUC from Genotype Component 2: 0.628571428571429"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.6"
## [1] "***********************************************************"
## [1] "Working with split No.9"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 1
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.914285714285714"
## [1] "Classification ROC AUC from Expression Component 1: 0.876190476190476"
## [1] "Classification ROC AUC from Methylation Component 1: 0.904761904761905"
## [1] "Classification ROC AUC from Genotype Component 1: 0.447619047619048"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.580952380952381"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 0 2
## [1] "Classification Accuracy from PLS Component 2: 94"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.942857142857143"
## [1] "Classification ROC AUC from Methylation Component 2: 0.866666666666667"
## [1] "Classification ROC AUC from Genotype Component 2: 0.504761904761905"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.561904761904762"
## [1] "***********************************************************"
## [1] "Working with split No.10"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 3
## 1 0 4
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.973214285714286"
## [1] "Classification ROC AUC from Expression Component 1: 0.946428571428571"
## [1] "Classification ROC AUC from Methylation Component 1: 0.892857142857143"
## [1] "Classification ROC AUC from Genotype Component 1: 0.642857142857143"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.598214285714286"
## Y.test
## DIABLO_predict2 0 1
## 0 13 1
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.991071428571429"
## [1] "Classification ROC AUC from Expression Component 2: 0.991071428571429"
## [1] "Classification ROC AUC from Methylation Component 2: 0.973214285714286"
## [1] "Classification ROC AUC from Genotype Component 2: 0.491071428571429"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.580357142857143"
## [1] "***********************************************************"
## [1] "Working with split No.11"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 17 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 1: 91"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 0.952941176470588"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.470588235294118"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.635294117647059"
## Y.test
## DIABLO_predict2 0 1
## 0 17 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 91"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Expression Component 2: 0.964705882352941"
## [1] "Classification ROC AUC from Methylation Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Genotype Component 2: 0.588235294117647"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.576470588235294"
## [1] "***********************************************************"
## [1] "Working with split No.12"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 10 0
## 1 0 8
## [1] "Classification Accuracy from PLS Component 1: 100"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.933884297520661"
## [1] "Classification ROC AUC from Expression Component 1: 0.917355371900826"
## [1] "Classification ROC AUC from Methylation Component 1: 0.834710743801653"
## [1] "Classification ROC AUC from Genotype Component 1: 0.396694214876033"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.520661157024793"
## Y.test
## DIABLO_predict2 0 1
## 0 9 1
## 1 0 9
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.983471074380165"
## [1] "Classification ROC AUC from Expression Component 2: 0.983471074380165"
## [1] "Classification ROC AUC from Methylation Component 2: 0.950413223140496"
## [1] "Classification ROC AUC from Genotype Component 2: 0.545454545454546"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.553719008264463"
## [1] "***********************************************************"
## [1] "Working with split No.13"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 5
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 77"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.991666666666667"
## [1] "Classification ROC AUC from Expression Component 1: 0.975"
## [1] "Classification ROC AUC from Methylation Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.491666666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.366666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 12 5
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 77"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.858333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.866666666666667"
## [1] "Classification ROC AUC from Methylation Component 2: 0.85"
## [1] "Classification ROC AUC from Genotype Component 2: 0.416666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.391666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.14"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 0
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.979166666666667"
## [1] "Classification ROC AUC from Expression Component 1: 0.96875"
## [1] "Classification ROC AUC from Methylation Component 1: 0.854166666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.302083333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.729166666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.989583333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.96875"
## [1] "Classification ROC AUC from Methylation Component 2: 0.927083333333333"
## [1] "Classification ROC AUC from Genotype Component 2: 0.208333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.708333333333333"
## [1] "***********************************************************"
## [1] "Working with split No.15"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 8 2
## 1 3 8
## [1] "Classification Accuracy from PLS Component 1: 76"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.867768595041322"
## [1] "Classification ROC AUC from Expression Component 1: 0.851239669421488"
## [1] "Classification ROC AUC from Methylation Component 1: 0.892561983471074"
## [1] "Classification ROC AUC from Genotype Component 1: 0.512396694214876"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.462809917355372"
## Y.test
## DIABLO_predict2 0 1
## 0 8 2
## 1 1 9
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.917355371900826"
## [1] "Classification ROC AUC from Expression Component 2: 0.925619834710744"
## [1] "Classification ROC AUC from Methylation Component 2: 0.925619834710744"
## [1] "Classification ROC AUC from Genotype Component 2: 0.603305785123967"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.454545454545455"
## [1] "***********************************************************"
## [1] "Working with split No.16"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 3
## 1 0 6
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.958333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.891666666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.891666666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.525"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.483333333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 12 2
## 1 0 7
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.975"
## [1] "Classification ROC AUC from Expression Component 2: 0.983333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.95"
## [1] "Classification ROC AUC from Genotype Component 2: 0.583333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.5"
## [1] "***********************************************************"
## [1] "Working with split No.17"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 17 2
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.930555555555556"
## [1] "Classification ROC AUC from Expression Component 1: 0.875"
## [1] "Classification ROC AUC from Methylation Component 1: 0.972222222222222"
## [1] "Classification ROC AUC from Genotype Component 1: 0.402777777777778"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.680555555555556"
## Y.test
## DIABLO_predict2 0 1
## 0 18 2
## 1 0 1
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.958333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.958333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.875"
## [1] "Classification ROC AUC from Genotype Component 2: 0.444444444444444"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.680555555555556"
## [1] "***********************************************************"
## [1] "Working with split No.18"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 10 3
## 1 2 5
## [1] "Classification Accuracy from PLS Component 1: 75"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.928571428571429"
## [1] "Classification ROC AUC from Expression Component 1: 0.910714285714286"
## [1] "Classification ROC AUC from Methylation Component 1: 0.991071428571429"
## [1] "Classification ROC AUC from Genotype Component 1: 0.330357142857143"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.571428571428571"
## Y.test
## DIABLO_predict2 0 1
## 0 13 3
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 82"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.973214285714286"
## [1] "Classification ROC AUC from Expression Component 2: 0.901785714285714"
## [1] "Classification ROC AUC from Methylation Component 2: 0.991071428571429"
## [1] "Classification ROC AUC from Genotype Component 2: 0.267857142857143"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.544642857142857"
## [1] "***********************************************************"
## [1] "Working with split No.19"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 100"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 0.988235294117647"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.541176470588235"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.635294117647059"
## Y.test
## DIABLO_predict2 0 1
## 0 12 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.388235294117647"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.588235294117647"
## [1] "***********************************************************"
## [1] "Working with split No.20"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 1
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 89"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.979166666666667"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 0.947916666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.354166666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.6875"
## Y.test
## DIABLO_predict2 0 1
## 0 15 2
## 1 0 2
## [1] "Classification Accuracy from PLS Component 2: 89"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.916666666666667"
## [1] "Classification ROC AUC from Expression Component 2: 0.9375"
## [1] "Classification ROC AUC from Methylation Component 2: 0.833333333333333"
## [1] "Classification ROC AUC from Genotype Component 2: 0.3125"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.666666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.21"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 17 1
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.263157894736842"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.491228070175439"
## Y.test
## DIABLO_predict2 0 1
## 0 18 1
## 1 0 2
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.964912280701754"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.175438596491228"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.508771929824561"
## [1] "***********************************************************"
## [1] "Working with split No.22"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 2
## 1 2 3
## [1] "Classification Accuracy from PLS Component 1: 82"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.870588235294118"
## [1] "Classification ROC AUC from Expression Component 1: 0.882352941176471"
## [1] "Classification ROC AUC from Methylation Component 1: 0.764705882352941"
## [1] "Classification ROC AUC from Genotype Component 1: 0.482352941176471"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.552941176470588"
## Y.test
## DIABLO_predict2 0 1
## 0 13 1
## 1 3 3
## [1] "Classification Accuracy from PLS Component 2: 80"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Expression Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Methylation Component 2: 0.929411764705882"
## [1] "Classification ROC AUC from Genotype Component 2: 0.470588235294118"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.564705882352941"
## [1] "***********************************************************"
## [1] "Working with split No.23"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 1
## 1 0 6
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.991071428571429"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 0.973214285714286"
## [1] "Classification ROC AUC from Genotype Component 1: 0.535714285714286"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.508928571428571"
## Y.test
## DIABLO_predict2 0 1
## 0 14 4
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 82"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.955357142857143"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.446428571428571"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.526785714285714"
## [1] "***********************************************************"
## [1] "Working with split No.24"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.952941176470588"
## [1] "Classification ROC AUC from Expression Component 1: 0.964705882352941"
## [1] "Classification ROC AUC from Methylation Component 1: 0.882352941176471"
## [1] "Classification ROC AUC from Genotype Component 1: 0.364705882352941"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.470588235294118"
## Y.test
## DIABLO_predict2 0 1
## 0 17 1
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.964705882352941"
## [1] "Classification ROC AUC from Expression Component 2: 0.964705882352941"
## [1] "Classification ROC AUC from Methylation Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Genotype Component 2: 0.270588235294118"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.564705882352941"
## [1] "***********************************************************"
## [1] "Working with split No.25"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 1
## 1 0 4
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.989583333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.96875"
## [1] "Classification ROC AUC from Methylation Component 1: 0.989583333333333"
## [1] "Classification ROC AUC from Genotype Component 1: 0.177083333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.84375"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 1 4
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.947916666666667"
## [1] "Classification ROC AUC from Expression Component 2: 0.947916666666667"
## [1] "Classification ROC AUC from Methylation Component 2: 0.78125"
## [1] "Classification ROC AUC from Genotype Component 2: 0.28125"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.854166666666667"
## [1] "***********************************************************"
## [1] "Working with split No.26"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 8 3
## 1 1 7
## [1] "Classification Accuracy from PLS Component 1: 79"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.883333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.825"
## [1] "Classification ROC AUC from Methylation Component 1: 0.941666666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.308333333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.541666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 10 3
## 1 1 6
## [1] "Classification Accuracy from PLS Component 2: 80"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.95"
## [1] "Classification ROC AUC from Expression Component 2: 0.95"
## [1] "Classification ROC AUC from Methylation Component 2: 0.966666666666667"
## [1] "Classification ROC AUC from Genotype Component 2: 0.216666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.483333333333333"
## [1] "***********************************************************"
## [1] "Working with split No.27"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 2
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.866666666666667"
## [1] "Classification ROC AUC from Expression Component 1: 0.895238095238095"
## [1] "Classification ROC AUC from Methylation Component 1: 0.847619047619048"
## [1] "Classification ROC AUC from Genotype Component 1: 0.39047619047619"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.619047619047619"
## Y.test
## DIABLO_predict2 0 1
## 0 13 3
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.990476190476191"
## [1] "Classification ROC AUC from Expression Component 2: 0.980952380952381"
## [1] "Classification ROC AUC from Methylation Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.19047619047619"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.6"
## [1] "***********************************************************"
## [1] "Working with split No.28"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 2
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.888888888888889"
## [1] "Classification ROC AUC from Expression Component 1: 0.875"
## [1] "Classification ROC AUC from Methylation Component 1: 0.819444444444444"
## [1] "Classification ROC AUC from Genotype Component 1: 0.388888888888889"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.763888888888889"
## Y.test
## DIABLO_predict2 0 1
## 0 16 2
## 1 1 2
## [1] "Classification Accuracy from PLS Component 2: 86"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.833333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.930555555555556"
## [1] "Classification ROC AUC from Methylation Component 2: 0.75"
## [1] "Classification ROC AUC from Genotype Component 2: 0.236111111111111"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.763888888888889"
## [1] "***********************************************************"
## [1] "Working with split No.29"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 0
## 1 1 3
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.902777777777778"
## [1] "Classification ROC AUC from Expression Component 1: 0.875"
## [1] "Classification ROC AUC from Methylation Component 1: 0.972222222222222"
## [1] "Classification ROC AUC from Genotype Component 1: 0.444444444444444"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.930555555555556"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 1 3
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.944444444444444"
## [1] "Classification ROC AUC from Expression Component 2: 0.944444444444444"
## [1] "Classification ROC AUC from Methylation Component 2: 0.861111111111111"
## [1] "Classification ROC AUC from Genotype Component 2: 0.333333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.888888888888889"
## [1] "***********************************************************"
## [1] "Working with split No.30"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 2
## 1 1 1
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.929411764705882"
## [1] "Classification ROC AUC from Expression Component 1: 0.882352941176471"
## [1] "Classification ROC AUC from Methylation Component 1: 0.835294117647059"
## [1] "Classification ROC AUC from Genotype Component 1: 0.517647058823529"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.458823529411765"
## Y.test
## DIABLO_predict2 0 1
## 0 16 3
## 1 0 1
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.905882352941176"
## [1] "Classification ROC AUC from Expression Component 2: 0.823529411764706"
## [1] "Classification ROC AUC from Methylation Component 2: 0.894117647058824"
## [1] "Classification ROC AUC from Genotype Component 2: 0.435294117647059"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.482352941176471"
## [1] "***********************************************************"
## [1] "Working with split No.31"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 1
## 1 4 6
## [1] "Classification Accuracy from PLS Component 1: 77"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.971428571428571"
## [1] "Classification ROC AUC from Expression Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.352380952380952"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.457142857142857"
## Y.test
## DIABLO_predict2 0 1
## 0 8 1
## 1 4 6
## [1] "Classification Accuracy from PLS Component 2: 74"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Expression Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.352380952380952"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.438095238095238"
## [1] "***********************************************************"
## [1] "Working with split No.32"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 0
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.941176470588235"
## [1] "Classification ROC AUC from Expression Component 1: 0.917647058823529"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.329411764705882"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.858823529411765"
## Y.test
## DIABLO_predict2 0 1
## 0 15 0
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.517647058823529"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.858823529411765"
## [1] "***********************************************************"
## [1] "Working with split No.33"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 0
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.941176470588235"
## [1] "Classification ROC AUC from Expression Component 1: 0.929411764705882"
## [1] "Classification ROC AUC from Methylation Component 1: 0.988235294117647"
## [1] "Classification ROC AUC from Genotype Component 1: 0.552941176470588"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.6"
## Y.test
## DIABLO_predict2 0 1
## 0 15 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Expression Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.447058823529412"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.623529411764706"
## [1] "***********************************************************"
## [1] "Working with split No.34"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 1
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Expression Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Methylation Component 1: 0.904761904761905"
## [1] "Classification ROC AUC from Genotype Component 1: 0.447619047619048"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.59047619047619"
## Y.test
## DIABLO_predict2 0 1
## 0 14 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.952380952380952"
## [1] "Classification ROC AUC from Genotype Component 2: 0.533333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.561904761904762"
## [1] "***********************************************************"
## [1] "Working with split No.35"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 10 4
## 1 1 3
## [1] "Classification Accuracy from PLS Component 1: 72"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.905982905982906"
## [1] "Classification ROC AUC from Expression Component 1: 0.888888888888889"
## [1] "Classification ROC AUC from Methylation Component 1: 0.871794871794872"
## [1] "Classification ROC AUC from Genotype Component 1: 0.632478632478632"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.615384615384615"
## Y.test
## DIABLO_predict2 0 1
## 0 13 3
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 86"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.948717948717949"
## [1] "Classification ROC AUC from Expression Component 2: 0.897435897435897"
## [1] "Classification ROC AUC from Methylation Component 2: 0.94017094017094"
## [1] "Classification ROC AUC from Genotype Component 2: 0.547008547008547"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.58974358974359"
## [1] "***********************************************************"
## [1] "Working with split No.36"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 10 1
## 1 1 6
## [1] "Classification Accuracy from PLS Component 1: 89"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.948717948717949"
## [1] "Classification ROC AUC from Expression Component 1: 0.957264957264957"
## [1] "Classification ROC AUC from Methylation Component 1: 0.94017094017094"
## [1] "Classification ROC AUC from Genotype Component 1: 0.376068376068376"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.623931623931624"
## Y.test
## DIABLO_predict2 0 1
## 0 12 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.982905982905983"
## [1] "Classification ROC AUC from Expression Component 2: 0.982905982905983"
## [1] "Classification ROC AUC from Methylation Component 2: 0.982905982905983"
## [1] "Classification ROC AUC from Genotype Component 2: 0.401709401709402"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.632478632478632"
## [1] "***********************************************************"
## [1] "Working with split No.37"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 3
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 82"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.955357142857143"
## [1] "Classification ROC AUC from Expression Component 1: 0.946428571428571"
## [1] "Classification ROC AUC from Methylation Component 1: 0.928571428571429"
## [1] "Classification ROC AUC from Genotype Component 1: 0.303571428571429"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.357142857142857"
## Y.test
## DIABLO_predict2 0 1
## 0 13 2
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.910714285714286"
## [1] "Classification ROC AUC from Expression Component 2: 0.9375"
## [1] "Classification ROC AUC from Methylation Component 2: 0.866071428571429"
## [1] "Classification ROC AUC from Genotype Component 2: 0.339285714285714"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.357142857142857"
## [1] "***********************************************************"
## [1] "Working with split No.38"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 3
## 1 5 2
## [1] "Classification Accuracy from PLS Component 1: 64"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.776470588235294"
## [1] "Classification ROC AUC from Expression Component 1: 0.8"
## [1] "Classification ROC AUC from Methylation Component 1: 0.788235294117647"
## [1] "Classification ROC AUC from Genotype Component 1: 0.364705882352941"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.458823529411765"
## Y.test
## DIABLO_predict2 0 1
## 0 14 1
## 1 2 3
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.929411764705882"
## [1] "Classification ROC AUC from Expression Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Methylation Component 2: 0.882352941176471"
## [1] "Classification ROC AUC from Genotype Component 2: 0.305882352941176"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.458823529411765"
## [1] "***********************************************************"
## [1] "Working with split No.39"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 1
## 1 0 6
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.971428571428571"
## [1] "Classification ROC AUC from Expression Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Methylation Component 1: 0.990476190476191"
## [1] "Classification ROC AUC from Genotype Component 1: 0.380952380952381"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.857142857142857"
## Y.test
## DIABLO_predict2 0 1
## 0 15 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.990476190476191"
## [1] "Classification ROC AUC from Methylation Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Genotype Component 2: 0.447619047619048"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.866666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.40"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 1
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 91"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.941176470588235"
## [1] "Classification ROC AUC from Expression Component 1: 0.964705882352941"
## [1] "Classification ROC AUC from Methylation Component 1: 0.905882352941176"
## [1] "Classification ROC AUC from Genotype Component 1: 0.423529411764706"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.541176470588235"
## Y.test
## DIABLO_predict2 0 1
## 0 17 1
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.882352941176471"
## [1] "Classification ROC AUC from Genotype Component 2: 0.529411764705882"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.552941176470588"
## [1] "***********************************************************"
## [1] "Working with split No.41"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 2
## 1 2 2
## [1] "Classification Accuracy from PLS Component 1: 81"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.894117647058824"
## [1] "Classification ROC AUC from Expression Component 1: 0.894117647058824"
## [1] "Classification ROC AUC from Methylation Component 1: 0.823529411764706"
## [1] "Classification ROC AUC from Genotype Component 1: 0.329411764705882"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.776470588235294"
## Y.test
## DIABLO_predict2 0 1
## 0 16 2
## 1 0 2
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.882352941176471"
## [1] "Classification ROC AUC from Expression Component 2: 0.905882352941176"
## [1] "Classification ROC AUC from Methylation Component 2: 0.823529411764706"
## [1] "Classification ROC AUC from Genotype Component 2: 0.235294117647059"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.776470588235294"
## [1] "***********************************************************"
## [1] "Working with split No.42"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 1
## 1 0 4
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.988235294117647"
## [1] "Classification ROC AUC from Expression Component 1: 0.929411764705882"
## [1] "Classification ROC AUC from Methylation Component 1: 0.988235294117647"
## [1] "Classification ROC AUC from Genotype Component 1: 0.317647058823529"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.517647058823529"
## Y.test
## DIABLO_predict2 0 1
## 0 16 1
## 1 1 4
## [1] "Classification Accuracy from PLS Component 2: 91"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.988235294117647"
## [1] "Classification ROC AUC from Expression Component 2: 0.964705882352941"
## [1] "Classification ROC AUC from Methylation Component 2: 0.988235294117647"
## [1] "Classification ROC AUC from Genotype Component 2: 0.352941176470588"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.505882352941176"
## [1] "***********************************************************"
## [1] "Working with split No.43"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 1
## 1 5 2
## [1] "Classification Accuracy from PLS Component 1: 68"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.912280701754386"
## [1] "Classification ROC AUC from Expression Component 1: 0.929824561403509"
## [1] "Classification ROC AUC from Methylation Component 1: 0.807017543859649"
## [1] "Classification ROC AUC from Genotype Component 1: 0.228070175438596"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.543859649122807"
## Y.test
## DIABLO_predict2 0 1
## 0 16 1
## 1 3 2
## [1] "Classification Accuracy from PLS Component 2: 82"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.947368421052632"
## [1] "Classification ROC AUC from Expression Component 2: 0.982456140350877"
## [1] "Classification ROC AUC from Methylation Component 2: 0.894736842105263"
## [1] "Classification ROC AUC from Genotype Component 2: 0.140350877192982"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.491228070175439"
## [1] "***********************************************************"
## [1] "Working with split No.44"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 8 1
## 1 2 9
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.942148760330578"
## [1] "Classification ROC AUC from Expression Component 1: 0.933884297520661"
## [1] "Classification ROC AUC from Methylation Component 1: 0.983471074380165"
## [1] "Classification ROC AUC from Genotype Component 1: 0.56198347107438"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.685950413223141"
## Y.test
## DIABLO_predict2 0 1
## 0 11 1
## 1 0 10
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.991735537190083"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.462809917355372"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.677685950413223"
## [1] "***********************************************************"
## [1] "Working with split No.45"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 0
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.944444444444444"
## [1] "Classification ROC AUC from Expression Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.958333333333333"
## [1] "Classification ROC AUC from Genotype Component 1: 0.402777777777778"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.833333333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 17 0
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.930555555555556"
## [1] "Classification ROC AUC from Genotype Component 2: 0.347222222222222"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.819444444444444"
## [1] "***********************************************************"
## [1] "Working with split No.46"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 2
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.876190476190476"
## [1] "Classification ROC AUC from Expression Component 1: 0.876190476190476"
## [1] "Classification ROC AUC from Methylation Component 1: 0.895238095238095"
## [1] "Classification ROC AUC from Genotype Component 1: 0.438095238095238"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.733333333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 15 2
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Expression Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.942857142857143"
## [1] "Classification ROC AUC from Genotype Component 2: 0.419047619047619"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.761904761904762"
## [1] "***********************************************************"
## [1] "Working with split No.47"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 2
## 1 2 3
## [1] "Classification Accuracy from PLS Component 1: 80"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.84375"
## [1] "Classification ROC AUC from Expression Component 1: 0.885416666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.8125"
## [1] "Classification ROC AUC from Genotype Component 1: 0.625"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.520833333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 16 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.9375"
## [1] "Classification ROC AUC from Expression Component 2: 0.947916666666667"
## [1] "Classification ROC AUC from Methylation Component 2: 0.916666666666667"
## [1] "Classification ROC AUC from Genotype Component 2: 0.572916666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.520833333333333"
## [1] "***********************************************************"
## [1] "Working with split No.48"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 1
## 1 1 6
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.875"
## [1] "Classification ROC AUC from Expression Component 1: 0.875"
## [1] "Classification ROC AUC from Methylation Component 1: 0.910714285714286"
## [1] "Classification ROC AUC from Genotype Component 1: 0.508928571428571"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.580357142857143"
## Y.test
## DIABLO_predict2 0 1
## 0 13 1
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.526785714285714"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.5625"
## [1] "***********************************************************"
## [1] "Working with split No.49"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 2
## 1 1 8
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Expression Component 1: 0.925"
## [1] "Classification ROC AUC from Methylation Component 1: 0.9"
## [1] "Classification ROC AUC from Genotype Component 1: 0.308333333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.75"
## Y.test
## DIABLO_predict2 0 1
## 0 10 0
## 1 1 9
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.966666666666667"
## [1] "Classification ROC AUC from Expression Component 2: 0.975"
## [1] "Classification ROC AUC from Methylation Component 2: 0.983333333333333"
## [1] "Classification ROC AUC from Genotype Component 2: 0.45"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.7"
## [1] "***********************************************************"
## [1] "Working with split No.50"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 2
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Expression Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Methylation Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Genotype Component 1: 0.438095238095238"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.523809523809524"
## Y.test
## DIABLO_predict2 0 1
## 0 14 2
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 86"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Expression Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Methylation Component 2: 0.857142857142857"
## [1] "Classification ROC AUC from Genotype Component 2: 0.266666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.523809523809524"
## [1] "***********************************************************"
## [1] "Working with split No.51"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 3
## 1 4 1
## [1] "Classification Accuracy from PLS Component 1: 67"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.819444444444444"
## [1] "Classification ROC AUC from Expression Component 1: 0.791666666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.875"
## [1] "Classification ROC AUC from Genotype Component 1: 0.291666666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.625"
## Y.test
## DIABLO_predict2 0 1
## 0 14 2
## 1 4 2
## [1] "Classification Accuracy from PLS Component 2: 73"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.833333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.861111111111111"
## [1] "Classification ROC AUC from Methylation Component 2: 0.736111111111111"
## [1] "Classification ROC AUC from Genotype Component 2: 0.305555555555556"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.680555555555556"
## [1] "***********************************************************"
## [1] "Working with split No.52"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 2
## 1 1 7
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.931623931623932"
## [1] "Classification ROC AUC from Expression Component 1: 0.923076923076923"
## [1] "Classification ROC AUC from Methylation Component 1: 0.991452991452991"
## [1] "Classification ROC AUC from Genotype Component 1: 0.179487179487179"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.632478632478632"
## Y.test
## DIABLO_predict2 0 1
## 0 9 1
## 1 1 8
## [1] "Classification Accuracy from PLS Component 2: 89"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.974358974358974"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.94017094017094"
## [1] "Classification ROC AUC from Genotype Component 2: 0.136752136752137"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.598290598290598"
## [1] "***********************************************************"
## [1] "Working with split No.53"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 1
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 89"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.270588235294118"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.658823529411765"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 1 4
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.964705882352941"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.258823529411765"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.635294117647059"
## [1] "***********************************************************"
## [1] "Working with split No.54"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 0
## 1 2 6
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Expression Component 1: 0.885714285714286"
## [1] "Classification ROC AUC from Methylation Component 1: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 1: 0.666666666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.723809523809524"
## Y.test
## DIABLO_predict2 0 1
## 0 14 1
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.990476190476191"
## [1] "Classification ROC AUC from Methylation Component 2: 0.980952380952381"
## [1] "Classification ROC AUC from Genotype Component 2: 0.523809523809524"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.733333333333333"
## [1] "***********************************************************"
## [1] "Working with split No.55"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 1
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 0.96875"
## [1] "Classification ROC AUC from Genotype Component 1: 0.604166666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.552083333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 15 2
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.958333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.927083333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.9375"
## [1] "Classification ROC AUC from Genotype Component 2: 0.583333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.53125"
## [1] "***********************************************************"
## [1] "Working with split No.56"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 1
## 1 2 6
## [1] "Classification Accuracy from PLS Component 1: 85"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.919642857142857"
## [1] "Classification ROC AUC from Expression Component 1: 0.928571428571429"
## [1] "Classification ROC AUC from Methylation Component 1: 0.928571428571429"
## [1] "Classification ROC AUC from Genotype Component 1: 0.410714285714286"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.642857142857143"
## Y.test
## DIABLO_predict2 0 1
## 0 12 2
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.919642857142857"
## [1] "Classification ROC AUC from Expression Component 2: 0.919642857142857"
## [1] "Classification ROC AUC from Methylation Component 2: 0.741071428571429"
## [1] "Classification ROC AUC from Genotype Component 2: 0.383928571428571"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.625"
## [1] "***********************************************************"
## [1] "Working with split No.57"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 1 6
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.919642857142857"
## [1] "Classification ROC AUC from Expression Component 1: 0.883928571428571"
## [1] "Classification ROC AUC from Methylation Component 1: 0.946428571428571"
## [1] "Classification ROC AUC from Genotype Component 1: 0.642857142857143"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.4375"
## Y.test
## DIABLO_predict2 0 1
## 0 12 0
## 1 1 5
## [1] "Classification Accuracy from PLS Component 2: 94"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.964285714285714"
## [1] "Classification ROC AUC from Expression Component 2: 0.955357142857143"
## [1] "Classification ROC AUC from Methylation Component 2: 0.883928571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.473214285714286"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.455357142857143"
## [1] "***********************************************************"
## [1] "Working with split No.58"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 0
## 1 3 4
## [1] "Classification Accuracy from PLS Component 1: 83"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.902777777777778"
## [1] "Classification ROC AUC from Expression Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.944444444444444"
## [1] "Classification ROC AUC from Genotype Component 1: 0.361111111111111"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.708333333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 14 0
## 1 2 3
## [1] "Classification Accuracy from PLS Component 2: 89"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.986111111111111"
## [1] "Classification ROC AUC from Expression Component 2: 0.986111111111111"
## [1] "Classification ROC AUC from Methylation Component 2: 0.902777777777778"
## [1] "Classification ROC AUC from Genotype Component 2: 0.333333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.680555555555556"
## [1] "***********************************************************"
## [1] "Working with split No.59"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 2 5
## [1] "Classification Accuracy from PLS Component 1: 81"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.847619047619048"
## [1] "Classification ROC AUC from Expression Component 1: 0.838095238095238"
## [1] "Classification ROC AUC from Methylation Component 1: 0.904761904761905"
## [1] "Classification ROC AUC from Genotype Component 1: 0.219047619047619"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.466666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 13 0
## 1 2 5
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.990476190476191"
## [1] "Classification ROC AUC from Methylation Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.19047619047619"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.495238095238095"
## [1] "***********************************************************"
## [1] "Working with split No.60"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 1
## 1 3 1
## [1] "Classification Accuracy from PLS Component 1: 80"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.894736842105263"
## [1] "Classification ROC AUC from Expression Component 1: 0.947368421052632"
## [1] "Classification ROC AUC from Methylation Component 1: 0.771929824561403"
## [1] "Classification ROC AUC from Genotype Component 1: 0.12280701754386"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.508771929824561"
## Y.test
## DIABLO_predict2 0 1
## 0 17 1
## 1 1 1
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.894736842105263"
## [1] "Classification ROC AUC from Expression Component 2: 0.929824561403509"
## [1] "Classification ROC AUC from Methylation Component 2: 0.789473684210526"
## [1] "Classification ROC AUC from Genotype Component 2: 0.210526315789474"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.543859649122807"
## [1] "***********************************************************"
## [1] "Working with split No.61"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 17 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 1: 91"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.964705882352941"
## [1] "Classification ROC AUC from Expression Component 1: 0.941176470588235"
## [1] "Classification ROC AUC from Methylation Component 1: 0.941176470588235"
## [1] "Classification ROC AUC from Genotype Component 1: 0.682352941176471"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.741176470588235"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 1 3
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.917647058823529"
## [1] "Classification ROC AUC from Expression Component 2: 0.905882352941176"
## [1] "Classification ROC AUC from Methylation Component 2: 0.764705882352941"
## [1] "Classification ROC AUC from Genotype Component 2: 0.435294117647059"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.788235294117647"
## [1] "***********************************************************"
## [1] "Working with split No.62"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 0
## 1 2 6
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 0.989583333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.114583333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.677083333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 15 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.1875"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.71875"
## [1] "***********************************************************"
## [1] "Working with split No.63"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 3 3
## [1] "Classification Accuracy from PLS Component 1: 75"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.894117647058824"
## [1] "Classification ROC AUC from Expression Component 1: 0.894117647058824"
## [1] "Classification ROC AUC from Methylation Component 1: 0.882352941176471"
## [1] "Classification ROC AUC from Genotype Component 1: 0.364705882352941"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.470588235294118"
## Y.test
## DIABLO_predict2 0 1
## 0 13 1
## 1 1 4
## [1] "Classification Accuracy from PLS Component 2: 89"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Expression Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Methylation Component 2: 0.941176470588235"
## [1] "Classification ROC AUC from Genotype Component 2: 0.223529411764706"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.470588235294118"
## [1] "***********************************************************"
## [1] "Working with split No.64"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 1
## 1 0 7
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.991071428571429"
## [1] "Classification ROC AUC from Expression Component 1: 0.982142857142857"
## [1] "Classification ROC AUC from Methylation Component 1: 0.964285714285714"
## [1] "Classification ROC AUC from Genotype Component 1: 0.339285714285714"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.678571428571429"
## Y.test
## DIABLO_predict2 0 1
## 0 14 0
## 1 0 7
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.910714285714286"
## [1] "Classification ROC AUC from Genotype Component 2: 0.294642857142857"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.651785714285714"
## [1] "***********************************************************"
## [1] "Working with split No.65"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 2
## 1 2 2
## [1] "Classification Accuracy from PLS Component 1: 80"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.882352941176471"
## [1] "Classification ROC AUC from Expression Component 1: 0.858823529411765"
## [1] "Classification ROC AUC from Methylation Component 1: 0.811764705882353"
## [1] "Classification ROC AUC from Genotype Component 1: 0.552941176470588"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.552941176470588"
## Y.test
## DIABLO_predict2 0 1
## 0 15 1
## 1 1 2
## [1] "Classification Accuracy from PLS Component 2: 89"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Expression Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Methylation Component 2: 0.882352941176471"
## [1] "Classification ROC AUC from Genotype Component 2: 0.447058823529412"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.529411764705882"
## [1] "***********************************************************"
## [1] "Working with split No.66"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 4
## 1 1 3
## [1] "Classification Accuracy from PLS Component 1: 76"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.955357142857143"
## [1] "Classification ROC AUC from Expression Component 1: 0.946428571428571"
## [1] "Classification ROC AUC from Methylation Component 1: 0.866071428571429"
## [1] "Classification ROC AUC from Genotype Component 1: 0.455357142857143"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.508928571428571"
## Y.test
## DIABLO_predict2 0 1
## 0 12 3
## 1 1 4
## [1] "Classification Accuracy from PLS Component 2: 80"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.919642857142857"
## [1] "Classification ROC AUC from Expression Component 2: 0.919642857142857"
## [1] "Classification ROC AUC from Methylation Component 2: 0.946428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.544642857142857"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.517857142857143"
## [1] "***********************************************************"
## [1] "Working with split No.67"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 1
## 1 1 3
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.958333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.958333333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 0.986111111111111"
## [1] "Classification ROC AUC from Genotype Component 1: 0.305555555555556"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.638888888888889"
## Y.test
## DIABLO_predict2 0 1
## 0 18 1
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.986111111111111"
## [1] "Classification ROC AUC from Expression Component 2: 0.972222222222222"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.375"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.638888888888889"
## [1] "***********************************************************"
## [1] "Working with split No.68"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 1
## 1 0 6
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.980952380952381"
## [1] "Classification ROC AUC from Expression Component 1: 0.980952380952381"
## [1] "Classification ROC AUC from Methylation Component 1: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 1: 0.371428571428571"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.59047619047619"
## Y.test
## DIABLO_predict2 0 1
## 0 15 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.428571428571429"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.552380952380952"
## [1] "***********************************************************"
## [1] "Working with split No.69"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 17 2
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Expression Component 1: 0.916666666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.888888888888889"
## [1] "Classification ROC AUC from Genotype Component 1: 0.125"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.694444444444444"
## Y.test
## DIABLO_predict2 0 1
## 0 17 0
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.972222222222222"
## [1] "Classification ROC AUC from Genotype Component 2: 0.194444444444444"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.666666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.70"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 17 1
## 1 0 3
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.972222222222222"
## [1] "Classification ROC AUC from Expression Component 1: 0.972222222222222"
## [1] "Classification ROC AUC from Methylation Component 1: 0.944444444444444"
## [1] "Classification ROC AUC from Genotype Component 1: 0.527777777777778"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.847222222222222"
## Y.test
## DIABLO_predict2 0 1
## 0 18 0
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.986111111111111"
## [1] "Classification ROC AUC from Genotype Component 2: 0.430555555555556"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.847222222222222"
## [1] "***********************************************************"
## [1] "Working with split No.71"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 100"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.717647058823529"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.647058823529412"
## Y.test
## DIABLO_predict2 0 1
## 0 16 0
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.905882352941176"
## [1] "Classification ROC AUC from Genotype Component 2: 0.588235294117647"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.611764705882353"
## [1] "***********************************************************"
## [1] "Working with split No.72"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 18 1
## 1 0 3
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.569444444444444"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.555555555555556"
## Y.test
## DIABLO_predict2 0 1
## 0 18 0
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.569444444444444"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.527777777777778"
## [1] "***********************************************************"
## [1] "Working with split No.73"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 2
## 1 1 7
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.908333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.858333333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 0.941666666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.591666666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.666666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 10 3
## 1 2 7
## [1] "Classification Accuracy from PLS Component 2: 77"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.941666666666667"
## [1] "Classification ROC AUC from Expression Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.825"
## [1] "Classification ROC AUC from Genotype Component 2: 0.466666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.683333333333333"
## [1] "***********************************************************"
## [1] "Working with split No.74"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 15 2
## 1 2 2
## [1] "Classification Accuracy from PLS Component 1: 81"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.882352941176471"
## [1] "Classification ROC AUC from Expression Component 1: 0.835294117647059"
## [1] "Classification ROC AUC from Methylation Component 1: 0.894117647058824"
## [1] "Classification ROC AUC from Genotype Component 1: 0.364705882352941"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.705882352941176"
## Y.test
## DIABLO_predict2 0 1
## 0 16 1
## 1 0 2
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.952941176470588"
## [1] "Classification ROC AUC from Expression Component 2: 0.929411764705882"
## [1] "Classification ROC AUC from Methylation Component 2: 0.988235294117647"
## [1] "Classification ROC AUC from Genotype Component 2: 0.517647058823529"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.658823529411765"
## [1] "***********************************************************"
## [1] "Working with split No.75"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 0
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 94"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Expression Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Methylation Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Genotype Component 1: 0.523809523809524"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.819047619047619"
## Y.test
## DIABLO_predict2 0 1
## 0 14 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Expression Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Methylation Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.495238095238095"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.79047619047619"
## [1] "***********************************************************"
## [1] "Working with split No.76"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 0
## 1 2 6
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Expression Component 1: 0.914285714285714"
## [1] "Classification ROC AUC from Methylation Component 1: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 1: 0.695238095238095"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.828571428571429"
## Y.test
## DIABLO_predict2 0 1
## 0 12 0
## 1 1 6
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.980952380952381"
## [1] "Classification ROC AUC from Methylation Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Genotype Component 2: 0.714285714285714"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.857142857142857"
## [1] "***********************************************************"
## [1] "Working with split No.77"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 2
## 1 0 4
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.980952380952381"
## [1] "Classification ROC AUC from Expression Component 1: 0.980952380952381"
## [1] "Classification ROC AUC from Methylation Component 1: 0.961904761904762"
## [1] "Classification ROC AUC from Genotype Component 1: 0.39047619047619"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.295238095238095"
## Y.test
## DIABLO_predict2 0 1
## 0 14 1
## 1 1 6
## [1] "Classification Accuracy from PLS Component 2: 91"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Expression Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Genotype Component 2: 0.647619047619048"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.285714285714286"
## [1] "***********************************************************"
## [1] "Working with split No.78"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 2
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.974358974358974"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 0.965811965811966"
## [1] "Classification ROC AUC from Genotype Component 1: 0.452991452991453"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.760683760683761"
## Y.test
## DIABLO_predict2 0 1
## 0 13 3
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 86"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.965811965811966"
## [1] "Classification ROC AUC from Genotype Component 2: 0.572649572649573"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.743589743589744"
## [1] "***********************************************************"
## [1] "Working with split No.79"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 4
## 1 0 2
## [1] "Classification Accuracy from PLS Component 1: 79"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Expression Component 1: 0.885714285714286"
## [1] "Classification ROC AUC from Methylation Component 1: 0.933333333333333"
## [1] "Classification ROC AUC from Genotype Component 1: 0.419047619047619"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.523809523809524"
## Y.test
## DIABLO_predict2 0 1
## 0 14 5
## 1 1 2
## [1] "Classification Accuracy from PLS Component 2: 73"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Expression Component 2: 0.990476190476191"
## [1] "Classification ROC AUC from Methylation Component 2: 0.895238095238095"
## [1] "Classification ROC AUC from Genotype Component 2: 0.533333333333333"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.504761904761905"
## [1] "***********************************************************"
## [1] "Working with split No.80"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 2
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 84"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Expression Component 1: 0.885714285714286"
## [1] "Classification ROC AUC from Methylation Component 1: 0.952380952380952"
## [1] "Classification ROC AUC from Genotype Component 1: 0.447619047619048"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.533333333333333"
## Y.test
## DIABLO_predict2 0 1
## 0 13 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Expression Component 2: 0.952380952380952"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.609523809523809"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.533333333333333"
## [1] "***********************************************************"
## [1] "Working with split No.81"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 1
## 1 2 3
## [1] "Classification Accuracy from PLS Component 1: 83"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.933333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Methylation Component 1: 0.752380952380952"
## [1] "Classification ROC AUC from Genotype Component 1: 0.514285714285714"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.485714285714286"
## Y.test
## DIABLO_predict2 0 1
## 0 12 1
## 1 2 5
## [1] "Classification Accuracy from PLS Component 2: 85"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.914285714285714"
## [1] "Classification ROC AUC from Expression Component 2: 0.942857142857143"
## [1] "Classification ROC AUC from Methylation Component 2: 0.904761904761905"
## [1] "Classification ROC AUC from Genotype Component 2: 0.466666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.466666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.82"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 0
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.958333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.930555555555556"
## [1] "Classification ROC AUC from Methylation Component 1: 0.819444444444444"
## [1] "Classification ROC AUC from Genotype Component 1: 0.375"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.666666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 18 0
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.916666666666667"
## [1] "Classification ROC AUC from Genotype Component 2: 0.277777777777778"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.708333333333333"
## [1] "***********************************************************"
## [1] "Working with split No.83"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 0 7
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 0.966666666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.45"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.841666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 12 0
## 1 0 7
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 0.983333333333333"
## [1] "Classification ROC AUC from Genotype Component 2: 0.366666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.791666666666667"
## [1] "***********************************************************"
## [1] "Working with split No.84"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 1
## 1 0 5
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.989583333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.979166666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.947916666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.552083333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.65625"
## Y.test
## DIABLO_predict2 0 1
## 0 14 0
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 1"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.510416666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.645833333333333"
## [1] "***********************************************************"
## [1] "Working with split No.85"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 3
## 1 2 4
## [1] "Classification Accuracy from PLS Component 1: 76"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.857142857142857"
## [1] "Classification ROC AUC from Expression Component 1: 0.830357142857143"
## [1] "Classification ROC AUC from Methylation Component 1: 0.803571428571429"
## [1] "Classification ROC AUC from Genotype Component 1: 0.428571428571429"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.535714285714286"
## Y.test
## DIABLO_predict2 0 1
## 0 11 3
## 1 3 3
## [1] "Classification Accuracy from PLS Component 2: 70"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.901785714285714"
## [1] "Classification ROC AUC from Expression Component 2: 0.9375"
## [1] "Classification ROC AUC from Methylation Component 2: 0.821428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.276785714285714"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.544642857142857"
## [1] "***********************************************************"
## [1] "Working with split No.86"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 1
## 1 1 2
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.964912280701754"
## [1] "Classification ROC AUC from Expression Component 1: 0.947368421052632"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.385964912280702"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.368421052631579"
## Y.test
## DIABLO_predict2 0 1
## 0 19 1
## 1 0 2
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.964912280701754"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.280701754385965"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.403508771929825"
## [1] "***********************************************************"
## [1] "Working with split No.87"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 1
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 89"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Expression Component 1: 0.933333333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Genotype Component 1: 0.533333333333333"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.580952380952381"
## Y.test
## DIABLO_predict2 0 1
## 0 11 0
## 1 3 5
## [1] "Classification Accuracy from PLS Component 2: 84"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.923809523809524"
## [1] "Classification ROC AUC from Methylation Component 2: 0.914285714285714"
## [1] "Classification ROC AUC from Genotype Component 2: 0.504761904761905"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.552380952380952"
## [1] "***********************************************************"
## [1] "Working with split No.88"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 84"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.980952380952381"
## [1] "Classification ROC AUC from Expression Component 1: 0.971428571428571"
## [1] "Classification ROC AUC from Methylation Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Genotype Component 1: 0.571428571428571"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.514285714285714"
## Y.test
## DIABLO_predict2 0 1
## 0 13 2
## 1 0 5
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.961904761904762"
## [1] "Classification ROC AUC from Methylation Component 2: 0.971428571428571"
## [1] "Classification ROC AUC from Genotype Component 2: 0.476190476190476"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.523809523809524"
## [1] "***********************************************************"
## [1] "Working with split No.89"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 0
## 1 3 2
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 1"
## [1] "Classification ROC AUC from Expression Component 1: 1"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.225"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.8"
## Y.test
## DIABLO_predict2 0 1
## 0 17 0
## 1 2 1
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.95"
## [1] "Classification ROC AUC from Expression Component 2: 0.95"
## [1] "Classification ROC AUC from Methylation Component 2: 0.775"
## [1] "Classification ROC AUC from Genotype Component 2: 0.25"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.85"
## [1] "***********************************************************"
## [1] "Working with split No.90"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 9 0
## 1 2 9
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.983333333333333"
## [1] "Classification ROC AUC from Expression Component 1: 0.983333333333333"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.5"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.691666666666667"
## Y.test
## DIABLO_predict2 0 1
## 0 10 0
## 1 0 9
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.991666666666667"
## [1] "Classification ROC AUC from Expression Component 2: 0.991666666666667"
## [1] "Classification ROC AUC from Methylation Component 2: 0.958333333333333"
## [1] "Classification ROC AUC from Genotype Component 2: 0.525"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.725"
## [1] "***********************************************************"
## [1] "Working with split No.91"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 1
## 1 1 6
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.982142857142857"
## [1] "Classification ROC AUC from Expression Component 1: 0.946428571428571"
## [1] "Classification ROC AUC from Methylation Component 1: 0.883928571428571"
## [1] "Classification ROC AUC from Genotype Component 1: 0.455357142857143"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.75"
## Y.test
## DIABLO_predict2 0 1
## 0 14 1
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.982142857142857"
## [1] "Classification ROC AUC from Expression Component 2: 0.964285714285714"
## [1] "Classification ROC AUC from Methylation Component 2: 0.955357142857143"
## [1] "Classification ROC AUC from Genotype Component 2: 0.401785714285714"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.767857142857143"
## [1] "***********************************************************"
## [1] "Working with split No.92"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 14 0
## 1 1 3
## [1] "Classification Accuracy from PLS Component 1: 94"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.964705882352941"
## [1] "Classification ROC AUC from Expression Component 1: 0.929411764705882"
## [1] "Classification ROC AUC from Methylation Component 1: 0.870588235294118"
## [1] "Classification ROC AUC from Genotype Component 1: 0.658823529411765"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.717647058823529"
## Y.test
## DIABLO_predict2 0 1
## 0 17 1
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 95"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Expression Component 2: 0.976470588235294"
## [1] "Classification ROC AUC from Methylation Component 2: 0.917647058823529"
## [1] "Classification ROC AUC from Genotype Component 2: 0.470588235294118"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.705882352941177"
## [1] "***********************************************************"
## [1] "Working with split No.93"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 16 2
## 1 0 3
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.96875"
## [1] "Classification ROC AUC from Expression Component 1: 0.979166666666667"
## [1] "Classification ROC AUC from Methylation Component 1: 0.979166666666667"
## [1] "Classification ROC AUC from Genotype Component 1: 0.385416666666667"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.46875"
## Y.test
## DIABLO_predict2 0 1
## 0 15 2
## 1 0 4
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.947916666666667"
## [1] "Classification ROC AUC from Expression Component 2: 0.927083333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 0.90625"
## [1] "Classification ROC AUC from Genotype Component 2: 0.291666666666667"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.427083333333333"
## [1] "***********************************************************"
## [1] "Working with split No.94"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 1
## 1 2 6
## [1] "Classification Accuracy from PLS Component 1: 86"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.990476190476191"
## [1] "Classification ROC AUC from Expression Component 1: 0.942857142857143"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.514285714285714"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.40952380952381"
## Y.test
## DIABLO_predict2 0 1
## 0 15 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Expression Component 2: 0.933333333333333"
## [1] "Classification ROC AUC from Methylation Component 2: 1"
## [1] "Classification ROC AUC from Genotype Component 2: 0.6"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.476190476190476"
## [1] "***********************************************************"
## [1] "Working with split No.95"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 3
## 1 1 5
## [1] "Classification Accuracy from PLS Component 1: 81"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.991452991452991"
## [1] "Classification ROC AUC from Expression Component 1: 0.982905982905983"
## [1] "Classification ROC AUC from Methylation Component 1: 0.974358974358974"
## [1] "Classification ROC AUC from Genotype Component 1: 0.427350427350427"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.487179487179487"
## Y.test
## DIABLO_predict2 0 1
## 0 13 2
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.974358974358974"
## [1] "Classification ROC AUC from Expression Component 2: 0.974358974358974"
## [1] "Classification ROC AUC from Methylation Component 2: 0.931623931623932"
## [1] "Classification ROC AUC from Genotype Component 2: 0.521367521367521"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.478632478632479"
## [1] "***********************************************************"
## [1] "Working with split No.96"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 0
## 1 2 7
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.88034188034188"
## [1] "Classification ROC AUC from Expression Component 1: 0.854700854700855"
## [1] "Classification ROC AUC from Methylation Component 1: 0.905982905982906"
## [1] "Classification ROC AUC from Genotype Component 1: 0.401709401709402"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.726495726495726"
## Y.test
## DIABLO_predict2 0 1
## 0 11 2
## 1 0 7
## [1] "Classification Accuracy from PLS Component 2: 90"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.931623931623932"
## [1] "Classification ROC AUC from Expression Component 2: 0.923076923076923"
## [1] "Classification ROC AUC from Methylation Component 2: 0.923076923076923"
## [1] "Classification ROC AUC from Genotype Component 2: 0.401709401709402"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.726495726495726"
## [1] "***********************************************************"
## [1] "Working with split No.97"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 13 0
## 1 1 7
## [1] "Classification Accuracy from PLS Component 1: 95"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.955357142857143"
## [1] "Classification ROC AUC from Expression Component 1: 0.9375"
## [1] "Classification ROC AUC from Methylation Component 1: 1"
## [1] "Classification ROC AUC from Genotype Component 1: 0.598214285714286"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.580357142857143"
## Y.test
## DIABLO_predict2 0 1
## 0 14 0
## 1 0 6
## [1] "Classification Accuracy from PLS Component 2: 100"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.991071428571429"
## [1] "Classification ROC AUC from Expression Component 2: 0.991071428571429"
## [1] "Classification ROC AUC from Methylation Component 2: 0.955357142857143"
## [1] "Classification ROC AUC from Genotype Component 2: 0.491071428571429"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.571428571428571"
## [1] "***********************************************************"
## [1] "Working with split No.98"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 9 0
## 1 4 7
## [1] "Classification Accuracy from PLS Component 1: 80"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Expression Component 1: 0.923809523809524"
## [1] "Classification ROC AUC from Methylation Component 1: 0.885714285714286"
## [1] "Classification ROC AUC from Genotype Component 1: 0.552380952380952"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.714285714285714"
## Y.test
## DIABLO_predict2 0 1
## 0 11 0
## 1 2 6
## [1] "Classification Accuracy from PLS Component 2: 89"
## [1] "Classification ROC AUC from DIABLO Component 2: 1"
## [1] "Classification ROC AUC from Expression Component 2: 0.990476190476191"
## [1] "Classification ROC AUC from Methylation Component 2: 0.942857142857143"
## [1] "Classification ROC AUC from Genotype Component 2: 0.552380952380952"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.742857142857143"
## [1] "***********************************************************"
## [1] "Working with split No.99"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 12 2
## 1 0 6
## [1] "Classification Accuracy from PLS Component 1: 90"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.946428571428571"
## [1] "Classification ROC AUC from Expression Component 1: 0.9375"
## [1] "Classification ROC AUC from Methylation Component 1: 0.919642857142857"
## [1] "Classification ROC AUC from Genotype Component 1: 0.357142857142857"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.589285714285714"
## Y.test
## DIABLO_predict2 0 1
## 0 13 2
## 1 1 6
## [1] "Classification Accuracy from PLS Component 2: 86"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.982142857142857"
## [1] "Classification ROC AUC from Expression Component 2: 0.964285714285714"
## [1] "Classification ROC AUC from Methylation Component 2: 0.973214285714286"
## [1] "Classification ROC AUC from Genotype Component 2: 0.241071428571429"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.642857142857143"
## [1] "***********************************************************"
## [1] "Working with split No.100"## Design matrix has changed to include Y; each block will be
## linked to Y.## Y.test
## DIABLO_predict1 0 1
## 0 11 3
## 1 1 4
## [1] "Classification Accuracy from PLS Component 1: 79"
## [1] "Classification ROC AUC from DIABLO Component 1: 0.82051282051282"
## [1] "Classification ROC AUC from Expression Component 1: 0.769230769230769"
## [1] "Classification ROC AUC from Methylation Component 1: 0.769230769230769"
## [1] "Classification ROC AUC from Genotype Component 1: 0.478632478632479"
## [1] "Classification ROC AUC from Phenotype Component 1: 0.572649572649573"
## Y.test
## DIABLO_predict2 0 1
## 0 11 5
## 1 0 3
## [1] "Classification Accuracy from PLS Component 2: 74"
## [1] "Classification ROC AUC from DIABLO Component 2: 0.965811965811966"
## [1] "Classification ROC AUC from Expression Component 2: 0.905982905982906"
## [1] "Classification ROC AUC from Methylation Component 2: 0.863247863247863"
## [1] "Classification ROC AUC from Genotype Component 2: 0.35042735042735"
## [1] "Classification ROC AUC from Phenotype Component 2: 0.547008547008547"
## [1] "***********************************************************"plot(colMeans(comp1_fpr),colMeans(comp1_tpr),col="red",type="o",ylab="SENSITIVITY (TPR)",xlab="1-SPECIFISITY (FPR)",pch=19)
lines(colMeans(comp1_fpr_expr),colMeans(comp1_tpr_expr),col="blue",type="o",pch=19)
lines(colMeans(comp1_fpr_meth),colMeans(comp1_tpr_meth),col="darkgreen",type="o",pch=19)
lines(colMeans(comp1_fpr_gen),colMeans(comp1_tpr_gen),col="darkorange",type="o",pch=19)
lines(colMeans(comp1_fpr_phen),colMeans(comp1_tpr_phen),col="magenta",type="o",pch=19)
lines(c(0,1),c(0,1),col="black")
legend("bottomright",legend=c(paste0("DIABLO COMP1 AUC = ",round(mean(comp1_auc),2)," +/- ",round(2*sd(comp1_auc),2)),paste0("EXPR COMP1 AUC = ",round(mean(comp1_auc_expr),2)," +/- ",round(2*sd(comp1_auc_expr),2)),paste0("METH COMP1 AUC = ",round(mean(comp1_auc_meth),2)," +/- ",round(2*sd(comp1_auc_meth),2)),paste0("GEN COMP1 AUC = ",round(mean(comp1_auc_gen),2)," +/- ",round(2*sd(comp1_auc_gen),2)),paste0("PHEN COMP1 AUC = ",round(mean(comp1_auc_phen),2)," +/- ",round(2*sd(comp1_auc_phen),2))),col=c("red","blue","darkgreen","darkorange","magenta"),inset=0.02,lty=c(1,1,1,1,1))
plot(colMeans(comp2_fpr),colMeans(comp2_tpr),col="red",type="o",ylab="SENSITIVITY (TPR)",xlab="1-SPECIFISITY (FPR)",pch=19)
lines(colMeans(comp2_fpr_expr),colMeans(comp2_tpr_expr),col="blue",type="o",pch=19)
lines(colMeans(comp2_fpr_meth),colMeans(comp2_tpr_meth),col="darkgreen",type="o",pch=19)
lines(colMeans(comp2_fpr_gen),colMeans(comp2_tpr_gen),col="darkorange",type="o",pch=19)
lines(colMeans(comp2_fpr_phen),colMeans(comp2_tpr_phen),col="magenta",type="o",pch=19)
lines(c(0,1),c(0,1),col="black")
legend("bottomright",legend=c(paste0("DIABLO COMP2 AUC = ",round(mean(comp2_auc),2)," +/- ",round(2*sd(comp2_auc),2)),paste0("EXPR COMP2 AUC = ",round(mean(comp2_auc_expr),2)," +/- ",round(2*sd(comp2_auc_expr),2)),paste0("METH COMP2 AUC = ",round(mean(comp2_auc_meth),2)," +/- ",round(2*sd(comp2_auc_meth),2)),paste0("GEN COMP2 AUC = ",round(mean(comp2_auc_gen),2)," +/- ",round(2*sd(comp2_auc_gen),2)),paste0("PHEN COMP2 AUC = ",round(mean(comp2_auc_phen),2)," +/- ",round(2*sd(comp2_auc_phen),2))),col=c("red","blue","darkgreen","darkorange","magenta"),inset=0.02,lty=c(1,1,1,1,1))
write.table(comp1_auc,file="Comp1_DIABLO_AUC.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp1_tpr,file="Comp1_DIABLO_TPR.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp1_fpr,file="Comp1_DIABLO_FPR.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp2_auc,file="Comp2_DIABLO_AUC.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp2_tpr,file="Comp2_DIABLO_TPR.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp2_fpr,file="Comp2_DIABLO_FPR.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp1_acc,file="Comp1_DIABLO_Acc.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")
write.table(comp2_acc,file="Comp2_DIABLO_Acc.txt",col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")Here we plot the histograms of the DIABLO prediction for components 1 and 2.
gc()## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 7143622 381.6 13003114 694.5 13003114 694.5
## Vcells 356944289 2723.3 880297686 6716.2 880173343 6715.2comp1_acc_arch<-as.numeric(scan("Comp1_DIABLO_Acc.txt",what="character"))
comp2_acc_arch<-as.numeric(scan("Comp2_DIABLO_Acc.txt",what="character"))
#comp1_acc_arch<-c(comp1_acc,comp1_acc_arch)
#comp2_acc_arch<-c(comp2_acc,comp2_acc_arch)
hist(comp1_acc_arch,breaks=20,xlab="ACCURACY",main="Accuracy T2D Prediction from DIABLO: PLS1",col="darkgreen",xlim=c(70,100))
abline(v=71,col="red",lwd=5)
mtext(paste0("Accuracy = ",mean(comp1_acc_arch)," +/- ",2*sd(comp1_acc_arch)))
hist(comp2_acc_arch,breaks=20,xlab="ACCURACY",main="Accuracy T2D Prediction from DIABLO: PLS2",col="darkgreen",xlim=c(70,100))
abline(v=71,col="red",lwd=5)
mtext(paste0("Accuracy = ",mean(comp2_acc_arch)," +/- ",2*sd(comp2_acc_arch)))
Now we will access the significance of DIABLO prediction compared to the naive model that predicts every new individual to be a non-diabetic since the NonT2D is the majority class, this naive model would achieve a high accuracy of 71%.
gc()## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 7145644 381.7 13003114 694.5 13003114 694.5
## Vcells 356948567 2723.4 880297686 6716.2 880173343 6715.2sum(comp1_acc_arch<=71)/length(comp1_acc_arch)## [1] 0.03sum(comp2_acc_arch<=71)/length(comp2_acc_arch)## [1] 0.01We conclude that the DIABLO predicts far better than the naive model. Now we will compare the accuracy of DIABLO prediction against the accuracy of predictions from the 4 individual OMICs.
library("RColorBrewer")
my_integr<-as.numeric(scan("Comp2_DIABLO_Acc.txt",what="character"))
my_expr<-as.numeric(scan("Comp2_PLS_Expr_Acc.txt",what="character"))
my_meth<-as.numeric(scan("Comp2_PLS_Meth_Acc.txt",what="character"))
my_gen<-as.numeric(scan("Comp2_PLS_Gen_Acc.txt",what="character"))
my_phen<-as.numeric(scan("Comp2_PLS_Phen_Acc.txt",what="character"))
boxplot(my_integr,my_expr,my_meth,col=brewer.pal(3,"Dark2"),names=c("DIABLO","EXPR","METH"),ylab="T2D PREDICTION ACCURACY",main="Comparison of T2D Prediction between DIABLO and Individual OMICs")
boxplot(my_integr,my_expr,my_meth,my_phen,my_gen,col=brewer.pal(5,"Dark2"),names=c("DIABLO","EXPR","METH","PHEN","GEN"),ylab="T2D PREDICTION ACCURACY",main="Comparison of T2D Prediction between DIABLO and Individual OMICs")
The conclusion we make here is that even though DIABLO marinally otperforms individual OMICs in sense of prediction accuracy, its prediction is largely driven by Expression and Methylation OMICs. So we do not see a dramatic boost in prediction when integrating multiple OMICs. This is probably due to the fact that Genotype and Phenotype OMICs do very poor prediction and puting it together with very predictive Methylation and Expression OMICs only contaminates the analysis.
Now we will rank all the features from all the 4 OMICs by how much they contribute to the final prediction based on multiple train-test splits of the available samples.
expr_features_comp1<-list(); expr_features_comp2<-list()
meth_features_comp1<-list(); meth_features_comp2<-list()
gen_features_comp1<-list(); gen_features_comp2<-list()
phen_features_comp1<-list(); phen_features_comp2<-list()
for(k in 1:N_repeat)
{
print(paste0("Working with split No.", k))
gc()
set.seed(k+100)
test_samples<-selected_ind[sample(1:length(selected_ind),round(length(selected_ind)*0.2))]
train_samples<-selected_ind[!selected_ind%in%test_samples]
Y.train<-as.factor(as.character(T2D[match(train_samples,rownames(T2D)),]))
Y.test<-as.factor(as.character(T2D[match(test_samples,rownames(T2D)),]))
X.train_expr<-expr[match(train_samples,rownames(expr)),]
X.test_expr<-expr[match(test_samples,rownames(expr)),]
expr_plsda<-plsda(X.train_expr, Y.train, ncomp=2)
features_expr1<-names(head(sort(abs(expr_plsda$loadings$X[,"comp1"]),decreasing=TRUE),50))
features_expr2<-names(head(sort(abs(expr_plsda$loadings$X[,"comp2"]),decreasing=TRUE),50))
X.train_expr_selected_features<-subset(X.train_expr,select=unique(c(features_expr1, features_expr2)))
X.test_expr_selected_features<-subset(X.test_expr,select=unique(c(features_expr1, features_expr2)))
X.train_meth<-meth[match(train_samples,rownames(meth)),]
X.test_meth<-meth[match(test_samples,rownames(meth)),]
meth_plsda<-plsda(X.train_meth, Y.train, ncomp=2)
features_meth1<-names(head(sort(abs(meth_plsda$loadings$X[,"comp1"]),decreasing=TRUE),50))
features_meth2<-names(head(sort(abs(meth_plsda$loadings$X[,"comp2"]),decreasing=TRUE),50))
X.train_meth_selected_features<-subset(X.train_meth,select=unique(c(features_meth1, features_meth2)))
X.test_meth_selected_features<-subset(X.test_meth,select=unique(c(features_meth1, features_meth2)))
X.train_gen<-gen[match(train_samples,rownames(gen)),]
X.test_gen<-gen[match(test_samples,rownames(gen)),]
gen_plsda<-plsda(X.train_gen, Y.train, ncomp=2)
features_gen1<-names(head(sort(abs(gen_plsda$loadings$X[,"comp1"]),decreasing=TRUE),20))
features_gen2<-names(head(sort(abs(gen_plsda$loadings$X[,"comp2"]),decreasing=TRUE),20))
X.train_gen_selected_features<-subset(X.train_gen,select=unique(c(features_gen1, features_gen2)))
X.test_gen_selected_features<-subset(X.test_gen,select=unique(c(features_gen1, features_gen2)))
X.train_phen<-phen[match(train_samples,rownames(phen)),]
X.test_phen<-phen[match(test_samples,rownames(phen)),]
data.train<-list(expr=X.train_expr_selected_features, meth=X.train_meth_selected_features,
gen=X.train_gen_selected_features, phen=X.train_phen)
design=matrix(0.1, ncol=length(data.train), nrow=length(data.train),
dimnames=list(names(data.train),names(data.train)))
diag(design)=0
design["expr","meth"]<-0.1
design["meth","expr"]<-0.1
design["meth","phen"]<-0.01
design["phen","meth"]<-0.01
design["expr","gen"]<-0.01
design["gen","expr"]<-0.01
design["meth","gen"]<-0.01
design["gen","meth"]<-0.01
ncomp=2
list.keepX = list("expr"=c(30,30), "meth"=c(30,30), "gen"=c(5,5), "phen"=c(4,4))
res = block.splsda(X=data.train,Y=Y.train,ncomp=ncomp,keepX=list.keepX,design=design,
scheme="horst",mode="regression",init="svd.single",near.zero.var=TRUE)
expr_features_comp1[[k]]<-as.data.frame(rank(sort(abs(res$loadings$expr[,"comp1"]),decreasing=TRUE)))
colnames(expr_features_comp1[[k]])<-paste0("iter",k)
expr_features_comp1[[k]]$GENE<-rownames(expr_features_comp1[[k]])
expr_features_comp2[[k]]<-as.data.frame(rank(sort(abs(res$loadings$expr[,"comp2"]),decreasing=TRUE)))
colnames(expr_features_comp2[[k]])<-paste0("iter",k)
expr_features_comp2[[k]]$GENE<-rownames(expr_features_comp2[[k]])
meth_features_comp1[[k]]<-as.data.frame(rank(sort(abs(res$loadings$meth[,"comp1"]),decreasing=TRUE)))
colnames(meth_features_comp1[[k]])<-paste0("iter",k)
meth_features_comp1[[k]]$GENE<-rownames(meth_features_comp1[[k]])
meth_features_comp2[[k]]<-as.data.frame(rank(sort(abs(res$loadings$meth[,"comp2"]),decreasing=TRUE)))
colnames(meth_features_comp2[[k]])<-paste0("iter",k)
meth_features_comp2[[k]]$GENE<-rownames(meth_features_comp2[[k]])
gen_features_comp1[[k]]<-as.data.frame(rank(sort(abs(res$loadings$gen[,"comp1"]),decreasing=TRUE)))
colnames(gen_features_comp1[[k]])<-paste0("iter",k)
gen_features_comp1[[k]]$GENE<-rownames(gen_features_comp1[[k]])
gen_features_comp2[[k]]<-as.data.frame(rank(sort(abs(res$loadings$gen[,"comp2"]),decreasing=TRUE)))
colnames(gen_features_comp2[[k]])<-paste0("iter",k)
gen_features_comp2[[k]]$GENE<-rownames(gen_features_comp2[[k]])
phen_features_comp1[[k]]<-as.data.frame(rank(sort(abs(res$loadings$phen[,"comp1"]),decreasing=TRUE)))
colnames(phen_features_comp1[[k]])<-paste0("iter",k)
phen_features_comp1[[k]]$GENE<-rownames(phen_features_comp1[[k]])
phen_features_comp2[[k]]<-as.data.frame(rank(sort(abs(res$loadings$phen[,"comp2"]),decreasing=TRUE)))
colnames(phen_features_comp2[[k]])<-paste0("iter",k)
phen_features_comp2[[k]]$GENE<-rownames(phen_features_comp2[[k]])
print("***********************************************************")
}## [1] "Working with split No.1"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.2"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.3"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.4"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.5"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.6"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.7"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.8"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.9"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.10"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.11"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.12"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.13"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.14"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.15"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.16"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.17"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.18"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.19"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.20"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.21"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.22"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.23"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.24"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.25"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.26"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.27"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.28"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.29"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.30"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.31"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.32"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.33"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.34"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.35"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.36"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.37"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.38"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.39"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.40"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.41"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.42"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.43"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.44"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.45"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.46"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.47"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.48"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.49"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.50"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.51"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.52"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.53"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.54"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.55"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.56"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.57"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.58"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.59"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.60"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.61"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.62"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.63"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.64"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.65"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.66"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.67"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.68"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.69"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.70"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.71"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.72"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.73"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.74"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.75"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.76"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.77"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.78"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.79"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.80"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.81"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.82"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.83"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.84"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.85"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.86"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.87"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.88"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.89"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.90"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.91"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.92"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.93"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.94"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.95"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.96"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.97"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.98"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.99"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"
## [1] "Working with split No.100"## Design matrix has changed to include Y; each block will be
## linked to Y.## [1] "***********************************************************"Finally. let us create a resulting list of features for each of the 4 OMICs ranked by their contribution to the T2D predictive model:
expr_features_comp1_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),expr_features_comp1)
rownames(expr_features_comp1_final)<-expr_features_comp1_final$GENE
expr_features_comp1_final$GENE<-NULL
expr_features_comp1_final[is.na(expr_features_comp1_final)]<-0
expr_features_comp1_final$total_rank<-rowSums(expr_features_comp1_final)
expr_features_comp1_final<-expr_features_comp1_final[order(-expr_features_comp1_final$total_rank),]
print(head(expr_features_comp1_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10
## OPRD1 93 92.0 93.0 95 96.0 92 96.0 93 91.0 96.0
## SLC2A2 84 91.0 91.0 94 91.0 90 91.0 92 89.0 85.0
## CHL1 91 90.0 92.0 91 92.0 91 88.0 90 90.0 92.0
## GRAMD2B 90 87.0 89.0 92 95.0 93 90.0 86 87.0 95.0
## FOXE1 92 94.0 94.0 93 93.0 89 87.0 91 92.0 83.0
## ELFN1 87 89.0 90.0 80 84.0 87 83.0 85 88.0 90.0
## GABRA2 88 93.0 88.0 89 94.0 88 84.0 89 86.0 81.0
## ARG2 89 73.0 86.0 82 85.0 81 93.0 87 83.0 91.0
## TFCP2L1 86 88.0 32.5 90 90.0 0 94.0 88 68.0 89.0
## BARX1 77 86.0 84.0 33 72.0 82 33.5 77 74.0 77.0
## CLTRN 0 85.0 83.0 78 73.0 83 85.0 82 82.0 75.0
## PCOLCE2 66 82.0 77.0 86 87.0 76 86.0 83 80.0 88.0
## RASGRP1 81 76.0 79.0 81 83.0 75 78.0 67 63.0 78.0
## PLA1A 68 81.0 66.0 69 69.0 71 74.0 80 73.0 93.0
## COMP 67 77.0 32.5 70 78.0 78 95.0 74 65.0 82.0
## MPP1 70 74.0 87.0 33 88.0 85 81.0 0 76.0 70.0
## GLRA1 74 80.0 75.0 66 89.0 86 0.0 75 84.0 0.0
## GCNT4 83 83.0 32.5 76 33.5 64 33.5 79 75.0 33.5
## HCN4 79 69.0 32.5 75 86.0 32 92.0 32 0.0 84.0
## PRELP 0 84.0 32.5 71 75.0 72 67.0 71 31.5 33.5
## RHOT1 73 32.5 32.5 84 33.5 0 76.0 64 64.0 0.0
## MRO 0 32.5 32.5 73 79.0 0 69.0 81 31.5 0.0
## GAD1 32 67.0 70.0 74 71.0 79 33.5 0 31.5 33.5
## NTN1 71 0.0 81.0 79 77.0 0 89.0 0 0.0 94.0
## DACH2 0 0.0 74.0 72 76.0 0 77.0 0 79.0 0.0
## DCX 32 0.0 71.0 33 33.5 32 0.0 69 85.0 0.0
## ARL4C 32 32.5 0.0 33 68.0 69 33.5 68 31.5 33.5
## TBC1D4 0 0.0 69.0 85 82.0 73 72.0 0 0.0 0.0
## CPXM2 0 75.0 32.5 88 33.5 32 0.0 32 31.5 0.0
## FFAR4 32 0.0 85.0 0 74.0 32 0.0 0 0.0 0.0
## SLC24A2 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## NOTUM 32 79.0 0.0 33 33.5 0 0.0 32 31.5 0.0
## LRRC2 32 0.0 0.0 33 0.0 32 0.0 65 31.5 74.0
## F11 0 32.5 0.0 0 0.0 77 0.0 72 77.0 33.5
## CMTR2 65 32.5 0.0 33 67.0 0 79.0 84 0.0 33.5
## LSAMP 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## CACNG5 32 32.5 0.0 33 0.0 32 33.5 32 31.5 33.5
## NIPAL4 32 32.5 0.0 0 0.0 70 33.5 32 31.5 0.0
## REEP1 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## TAGLN3 82 65.0 32.5 0 0.0 0 71.0 0 0.0 0.0
## SERPINE2 0 71.0 0.0 83 33.5 0 33.5 0 31.5 0.0
## CLCF1 76 32.5 32.5 0 0.0 0 73.0 32 31.5 76.0
## C1QTNF1 0 32.5 32.5 33 33.5 65 68.0 0 0.0 33.5
## TSKU 0 32.5 0.0 87 80.0 32 33.5 0 0.0 33.5
## KCNA1 32 32.5 32.5 33 0.0 0 33.5 32 31.5 33.5
## SV2B 32 32.5 32.5 33 33.5 0 33.5 32 0.0 33.5
## CA5B 32 72.0 32.5 0 0.0 0 0.0 76 78.0 0.0
## FSTL4 32 32.5 32.5 33 0.0 0 33.5 32 31.5 33.5
## SIX6 0 0.0 68.0 33 81.0 80 0.0 0 31.5 0.0
## DKK3 0 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## iter11 iter12 iter13 iter14 iter15 iter16 iter17 iter18 iter19
## OPRD1 94.0 95 94 93 90 93 94.0 97 96
## SLC2A2 92.0 88 89 92 85 84 96.0 94 94
## CHL1 88.0 92 90 90 87 89 98.0 93 89
## GRAMD2B 90.0 94 87 84 86 87 93.0 95 95
## FOXE1 91.0 90 92 91 91 90 97.0 92 87
## ELFN1 89.0 86 84 89 79 77 92.0 89 97
## GABRA2 93.0 74 95 87 84 92 95.0 86 93
## ARG2 77.0 70 86 77 88 88 91.0 96 77
## TFCP2L1 82.0 91 82 82 82 91 81.0 88 76
## BARX1 85.0 69 88 83 71 32 88.0 69 91
## CLTRN 84.0 77 81 88 80 0 86.0 34 85
## PCOLCE2 83.0 33 83 80 73 32 90.0 87 34
## RASGRP1 86.0 33 70 81 31 78 84.0 90 88
## PLA1A 75.0 84 78 72 67 65 87.0 34 34
## COMP 81.0 71 77 68 68 86 85.0 73 92
## MPP1 0.0 0 93 71 81 82 70.0 82 86
## GLRA1 76.0 0 0 78 70 81 89.0 91 0
## GCNT4 79.0 87 0 79 31 74 34.5 34 82
## HCN4 0.0 68 85 32 89 85 0.0 85 0
## PRELP 78.0 0 33 66 0 32 83.0 34 74
## RHOT1 0.0 76 0 67 0 0 34.5 0 69
## MRO 65.0 83 73 74 69 72 0.0 0 0
## GAD1 32.5 33 80 75 31 32 0.0 34 79
## NTN1 0.0 33 71 32 77 83 0.0 79 34
## DACH2 0.0 0 0 86 78 76 0.0 0 0
## DCX 32.5 0 0 85 83 79 34.5 78 0
## ARL4C 71.0 33 79 32 31 32 74.0 76 90
## TBC1D4 0.0 75 0 70 76 0 0.0 0 0
## CPXM2 72.0 33 33 32 31 32 34.5 34 34
## FFAR4 0.0 0 75 0 66 0 34.5 81 84
## SLC24A2 32.5 33 74 32 31 32 34.5 34 34
## NOTUM 32.5 0 0 32 31 0 34.5 70 34
## LRRC2 32.5 33 0 32 31 73 34.5 68 34
## F11 80.0 85 33 32 31 80 82.0 0 34
## CMTR2 0.0 89 0 32 0 70 0.0 34 34
## LSAMP 32.5 33 33 32 31 32 34.5 34 34
## CACNG5 32.5 33 72 32 31 32 34.5 34 0
## NIPAL4 32.5 33 33 32 31 32 34.5 34 71
## REEP1 32.5 33 0 32 0 32 34.5 34 34
## TAGLN3 0.0 0 67 32 31 0 0.0 77 0
## SERPINE2 87.0 0 0 32 0 68 72.0 34 0
## CLCF1 32.5 72 0 0 0 71 80.0 0 34
## C1QTNF1 67.0 0 0 0 0 0 73.0 72 81
## TSKU 0.0 93 76 0 74 67 34.5 0 80
## KCNA1 32.5 0 0 32 31 32 34.5 34 34
## SV2B 32.5 33 0 32 31 0 34.5 34 34
## CA5B 68.0 33 0 0 0 0 0.0 0 34
## FSTL4 32.5 0 33 32 0 32 34.5 34 34
## SIX6 0.0 33 66 32 31 0 79.0 0 83
## DKK3 32.5 0 33 32 0 0 34.5 34 34
## iter20 iter21 iter22 iter23 iter24 iter25 iter26 iter27 iter28
## OPRD1 88.0 94.0 94.0 97 96.0 92.0 93 91 91.0
## SLC2A2 90.0 93.0 88.0 96 94.0 89.0 95 93 86.0
## CHL1 87.0 89.0 90.0 93 92.0 86.0 94 90 87.0
## GRAMD2B 84.0 90.0 92.0 91 93.0 87.0 88 87 88.0
## FOXE1 89.0 92.0 93.0 95 95.0 90.0 92 92 90.0
## ELFN1 85.0 91.0 89.0 94 91.0 88.0 90 89 83.0
## GABRA2 86.0 82.0 87.0 92 90.0 91.0 91 84 92.0
## ARG2 83.0 86.0 84.0 90 82.0 81.0 86 85 85.0
## TFCP2L1 66.0 78.0 91.0 89 86.0 82.0 77 83 31.5
## BARX1 82.0 88.0 85.0 87 89.0 85.0 84 82 77.0
## CLTRN 81.0 85.0 83.0 85 84.0 80.0 0 81 82.0
## PCOLCE2 77.0 87.0 32.5 88 83.0 73.0 33 68 72.0
## RASGRP1 79.0 83.0 86.0 83 80.0 84.0 75 86 78.0
## PLA1A 74.0 75.0 80.0 79 88.0 77.0 33 0 89.0
## COMP 62.0 84.0 32.5 34 67.0 83.0 73 0 84.0
## MPP1 75.0 80.0 79.0 69 87.0 70.0 85 79 81.0
## GLRA1 76.0 68.0 76.0 82 81.0 78.0 89 88 79.0
## GCNT4 30.5 71.0 77.0 80 0.0 74.0 33 72 68.0
## HCN4 68.0 32.5 75.0 70 74.0 79.0 69 67 80.0
## PRELP 73.0 74.0 0.0 77 33.5 67.0 78 32 76.0
## RHOT1 30.5 70.0 81.0 84 73.0 31.5 0 32 71.0
## MRO 0.0 32.5 73.0 34 85.0 0.0 0 32 31.5
## GAD1 78.0 32.5 32.5 34 33.5 76.0 33 32 74.0
## NTN1 63.0 79.0 69.0 68 75.0 0.0 0 0 0.0
## DACH2 69.0 77.0 70.0 0 0.0 71.0 79 74 0.0
## DCX 65.0 0.0 82.0 0 0.0 68.0 33 73 0.0
## ARL4C 70.0 81.0 32.5 34 69.0 31.5 72 32 31.5
## TBC1D4 72.0 0.0 0.0 0 79.0 0.0 0 65 0.0
## CPXM2 64.0 32.5 32.5 34 33.5 31.5 33 32 31.5
## FFAR4 71.0 76.0 32.5 72 70.0 0.0 83 70 73.0
## SLC24A2 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## NOTUM 80.0 32.5 32.5 75 33.5 31.5 0 32 64.0
## LRRC2 0.0 32.5 32.5 34 33.5 64.0 0 32 31.5
## F11 0.0 0.0 72.0 0 33.5 72.0 33 32 31.5
## CMTR2 0.0 32.5 32.5 78 0.0 31.5 33 0 31.5
## LSAMP 30.5 32.5 32.5 34 33.5 31.5 33 32 0.0
## CACNG5 30.5 32.5 32.5 34 33.5 31.5 0 32 0.0
## NIPAL4 0.0 67.0 32.5 34 33.5 31.5 82 32 66.0
## REEP1 30.5 32.5 32.5 0 33.5 31.5 33 32 31.5
## TAGLN3 0.0 32.5 32.5 0 33.5 0.0 66 0 0.0
## SERPINE2 30.5 0.0 32.5 81 33.5 0.0 0 64 0.0
## CLCF1 0.0 0.0 32.5 0 33.5 69.0 0 0 31.5
## C1QTNF1 30.5 66.0 0.0 34 68.0 0.0 81 32 70.0
## TSKU 0.0 65.0 0.0 74 33.5 0.0 0 0 0.0
## KCNA1 30.5 32.5 32.5 34 33.5 31.5 0 0 31.5
## SV2B 30.5 73.0 32.5 34 0.0 31.5 0 32 0.0
## CA5B 0.0 0.0 32.5 0 33.5 75.0 0 0 0.0
## FSTL4 30.5 32.5 32.5 0 33.5 31.5 0 0 31.5
## SIX6 67.0 32.5 0.0 0 0.0 66.0 0 0 75.0
## DKK3 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## iter29 iter30 iter31 iter32 iter33 iter34 iter35 iter36 iter37
## OPRD1 93 95 94 94.0 92.0 88 98.0 96.0 91
## SLC2A2 92 94 91 87.0 89.0 92 97.0 94.0 87
## CHL1 90 91 88 90.0 87.0 91 96.0 91.0 86
## GRAMD2B 87 92 93 91.0 88.0 89 95.0 89.0 89
## FOXE1 91 93 90 93.0 90.0 93 94.0 95.0 92
## ELFN1 88 90 95 89.0 85.0 90 86.0 93.0 90
## GABRA2 89 89 83 85.0 91.0 86 93.0 92.0 93
## ARG2 76 80 85 92.0 78.0 84 91.0 85.0 79
## TFCP2L1 82 79 0 81.0 86.0 85 92.0 86.0 32
## BARX1 80 88 75 75.0 82.0 76 34.5 88.0 88
## CLTRN 84 87 86 73.0 77.0 87 85.0 87.0 78
## PCOLCE2 32 81 87 71.0 76.0 77 88.0 79.0 85
## RASGRP1 81 83 0 79.0 84.0 72 0.0 76.0 84
## PLA1A 69 82 78 72.0 70.0 73 34.5 81.0 74
## COMP 77 33 92 32.5 67.0 32 83.0 75.0 82
## MPP1 66 72 0 84.0 0.0 74 90.0 77.0 77
## GLRA1 71 86 0 83.0 79.0 0 82.0 82.0 0
## GCNT4 85 71 73 70.0 74.0 80 0.0 69.0 0
## HCN4 0 0 81 66.0 75.0 70 80.0 90.0 64
## PRELP 73 85 77 32.5 64.0 32 78.0 33.5 80
## RHOT1 0 75 0 67.0 31.5 75 34.5 0.0 0
## MRO 78 33 74 69.0 83.0 66 34.5 80.0 0
## GAD1 32 33 84 32.5 0.0 69 34.5 33.5 76
## NTN1 0 0 0 65.0 69.0 0 87.0 74.0 70
## DACH2 83 0 0 88.0 0.0 71 75.0 0.0 32
## DCX 64 0 69 86.0 31.5 83 0.0 73.0 0
## ARL4C 32 33 70 0.0 31.5 32 34.5 0.0 65
## TBC1D4 0 84 0 82.0 73.0 82 81.0 78.0 0
## CPXM2 75 33 33 32.5 72.0 32 0.0 0.0 32
## FFAR4 0 0 0 32.5 0.0 0 0.0 0.0 75
## SLC24A2 32 33 33 32.5 31.5 32 34.5 33.5 83
## NOTUM 32 33 33 0.0 31.5 32 0.0 84.0 32
## LRRC2 65 33 0 32.5 31.5 32 34.5 33.5 0
## F11 32 33 67 32.5 31.5 0 0.0 0.0 72
## CMTR2 74 33 33 32.5 81.0 32 0.0 33.5 0
## LSAMP 32 33 33 32.5 31.5 32 34.5 33.5 32
## CACNG5 32 33 33 32.5 31.5 32 34.5 33.5 32
## NIPAL4 0 0 33 0.0 0.0 32 0.0 0.0 69
## REEP1 32 33 33 32.5 31.5 32 34.5 33.5 32
## TAGLN3 0 66 0 32.5 0.0 81 84.0 0.0 32
## SERPINE2 72 33 68 0.0 31.5 0 70.0 0.0 32
## CLCF1 32 0 33 32.5 31.5 32 0.0 0.0 0
## C1QTNF1 0 33 33 0.0 0.0 32 0.0 0.0 68
## TSKU 0 76 66 0.0 0.0 0 74.0 83.0 0
## KCNA1 32 0 33 32.5 31.5 32 34.5 33.5 32
## SV2B 32 33 33 32.5 31.5 32 0.0 33.5 32
## CA5B 86 67 89 32.5 31.5 32 0.0 0.0 32
## FSTL4 32 33 33 32.5 31.5 32 34.5 33.5 32
## SIX6 0 0 33 0.0 31.5 0 0.0 0.0 81
## DKK3 0 33 33 0.0 31.5 32 34.5 33.5 32
## iter38 iter39 iter40 iter41 iter42 iter43 iter44 iter45 iter46
## OPRD1 97 94.0 89 93.0 93 94.0 94.0 94 97
## SLC2A2 88 92.0 85 91.0 88 93.0 92.0 95 96
## CHL1 95 90.0 86 90.0 90 91.0 88.0 93 88
## GRAMD2B 94 88.0 87 88.0 91 89.0 90.0 91 94
## FOXE1 93 91.0 88 92.0 89 92.0 0.0 92 91
## ELFN1 89 86.0 83 89.0 92 90.0 75.0 88 95
## GABRA2 92 93.0 84 94.0 86 87.0 70.0 86 93
## ARG2 96 74.0 75 70.0 87 88.0 91.0 82 79
## TFCP2L1 87 87.0 73 78.0 82 79.0 93.0 80 92
## BARX1 34 89.0 81 87.0 76 84.0 0.0 83 89
## CLTRN 34 82.0 82 83.0 73 86.0 0.0 85 90
## PCOLCE2 34 83.0 77 85.0 83 66.0 32.5 33 83
## RASGRP1 82 80.0 67 32.5 0 73.0 87.0 78 76
## PLA1A 34 70.0 76 82.0 85 68.0 0.0 89 86
## COMP 70 78.0 74 81.0 84 78.0 32.5 71 0
## MPP1 86 84.0 78 66.0 0 80.0 0.0 84 72
## GLRA1 83 76.0 70 79.0 0 85.0 72.0 81 0
## GCNT4 0 71.0 80 84.0 78 82.0 85.0 90 68
## HCN4 77 81.0 0 32.5 0 83.0 80.0 33 77
## PRELP 81 32.5 0 77.0 68 32.5 78.0 33 71
## RHOT1 69 0.0 79 65.0 0 69.0 73.0 79 34
## MRO 0 73.0 0 71.0 0 32.5 0.0 66 75
## GAD1 34 66.0 71 32.5 32 32.5 32.5 33 34
## NTN1 68 85.0 61 72.0 0 0.0 0.0 0 80
## DACH2 91 75.0 0 74.0 0 81.0 0.0 87 0
## DCX 34 67.0 30 0.0 0 72.0 0.0 33 0
## ARL4C 34 32.5 30 32.5 32 32.5 79.0 33 0
## TBC1D4 90 0.0 72 76.0 0 71.0 0.0 0 81
## CPXM2 0 32.5 30 32.5 32 32.5 32.5 33 87
## FFAR4 75 77.0 0 0.0 0 0.0 32.5 0 34
## SLC24A2 34 32.5 30 32.5 32 32.5 32.5 33 34
## NOTUM 0 32.5 0 32.5 32 32.5 32.5 33 0
## LRRC2 0 32.5 30 0.0 81 32.5 89.0 33 34
## F11 0 65.0 69 32.5 80 32.5 0.0 33 0
## CMTR2 0 32.5 30 32.5 65 67.0 86.0 75 0
## LSAMP 34 32.5 30 32.5 32 32.5 32.5 33 34
## CACNG5 34 32.5 30 32.5 32 32.5 32.5 33 34
## NIPAL4 0 32.5 60 0.0 32 0.0 32.5 33 0
## REEP1 34 32.5 30 32.5 32 32.5 0.0 33 34
## TAGLN3 85 0.0 62 0.0 66 77.0 0.0 70 0
## SERPINE2 34 32.5 63 80.0 0 0.0 65.0 0 78
## CLCF1 34 68.0 65 32.5 32 32.5 71.0 33 34
## C1QTNF1 79 0.0 64 0.0 0 32.5 32.5 33 0
## TSKU 74 32.5 0 69.0 0 0.0 0.0 68 84
## KCNA1 0 32.5 30 32.5 0 32.5 32.5 33 34
## SV2B 34 32.5 30 0.0 32 32.5 0.0 33 0
## CA5B 0 32.5 0 32.5 79 32.5 0.0 0 0
## FSTL4 34 32.5 30 32.5 32 32.5 32.5 33 34
## SIX6 0 32.5 0 86.0 0 0.0 0.0 0 0
## DKK3 34 32.5 30 32.5 0 32.5 0.0 33 0
## iter47 iter48 iter49 iter50 iter51 iter52 iter53 iter54 iter55
## OPRD1 94.0 93.0 97.0 94 91.0 88 97 98 91
## SLC2A2 89.0 94.0 95.0 95 87.0 89 94 92 88
## CHL1 92.0 92.0 96.0 89 90.0 84 87 82 85
## GRAMD2B 90.0 89.0 94.0 88 86.0 86 95 94 82
## FOXE1 93.0 91.0 98.0 92 88.0 90 93 87 89
## ELFN1 88.0 84.0 87.0 90 89.0 87 96 97 90
## GABRA2 91.0 74.0 86.0 93 92.0 91 88 95 83
## ARG2 86.0 90.0 93.0 77 85.0 85 90 99 79
## TFCP2L1 87.0 86.0 89.0 33 31.5 74 89 93 73
## BARX1 85.0 77.0 79.0 91 83.0 75 85 77 84
## CLTRN 72.0 73.0 71.0 75 79.0 72 78 85 87
## PCOLCE2 78.0 65.0 88.0 79 63.0 76 91 35 78
## RASGRP1 65.0 85.0 90.0 82 81.0 78 92 76 68
## PLA1A 75.0 0.0 77.0 33 84.0 0 83 86 76
## COMP 66.0 32.5 34.5 33 74.0 31 81 81 72
## MPP1 80.0 87.0 80.0 86 64.0 83 86 35 31
## GLRA1 84.0 88.0 85.0 78 82.0 82 77 0 70
## GCNT4 69.0 82.0 34.5 0 78.0 0 0 35 69
## HCN4 73.0 32.5 75.0 0 75.0 71 80 96 81
## PRELP 0.0 32.5 34.5 81 31.5 31 71 35 31
## RHOT1 74.0 75.0 70.0 0 80.0 0 0 78 0
## MRO 77.0 0.0 0.0 0 67.0 31 72 35 86
## GAD1 32.5 32.5 0.0 74 72.0 81 34 35 80
## NTN1 70.0 0.0 82.0 33 31.5 31 79 79 63
## DACH2 0.0 79.0 84.0 83 76.0 0 74 0 74
## DCX 68.0 81.0 92.0 33 69.0 0 34 0 75
## ARL4C 32.5 32.5 34.5 87 0.0 0 34 0 31
## TBC1D4 82.0 78.0 0.0 0 0.0 0 0 91 71
## CPXM2 32.5 32.5 34.5 33 31.5 31 34 35 64
## FFAR4 0.0 68.0 91.0 76 0.0 73 84 89 0
## SLC24A2 32.5 32.5 34.5 68 31.5 68 34 35 31
## NOTUM 32.5 32.5 34.5 67 77.0 31 76 35 77
## LRRC2 32.5 32.5 34.5 0 0.0 31 34 35 31
## F11 76.0 32.5 34.5 0 65.0 0 70 0 0
## CMTR2 32.5 0.0 0.0 0 68.0 31 0 73 0
## LSAMP 32.5 32.5 34.5 33 31.5 31 34 35 31
## CACNG5 32.5 32.5 0.0 0 31.5 31 34 35 31
## NIPAL4 32.5 32.5 73.0 73 31.5 31 69 0 0
## REEP1 32.5 32.5 34.5 33 31.5 31 34 35 31
## TAGLN3 0.0 32.5 76.0 33 0.0 0 68 84 0
## SERPINE2 32.5 0.0 0.0 0 0.0 0 73 0 65
## CLCF1 32.5 32.5 69.0 0 31.5 0 0 88 0
## C1QTNF1 0.0 32.5 34.5 71 31.5 0 34 35 0
## TSKU 83.0 32.5 0.0 0 0.0 0 0 35 0
## KCNA1 32.5 32.5 34.5 0 31.5 0 34 35 31
## SV2B 32.5 32.5 34.5 33 31.5 31 34 35 31
## CA5B 32.5 0.0 34.5 33 31.5 31 0 0 31
## FSTL4 32.5 0.0 34.5 33 31.5 0 0 35 31
## SIX6 0.0 0.0 0.0 85 70.0 0 82 0 31
## DKK3 32.5 32.5 34.5 33 31.5 31 34 0 31
## iter56 iter57 iter58 iter59 iter60 iter61 iter62 iter63 iter64
## OPRD1 91 89 92.0 94.0 90.0 92 94.0 96.0 93.0
## SLC2A2 90 87 94.0 89.0 91.0 94 93.0 90.0 92.0
## CHL1 88 91 86.0 93.0 89.0 89 91.0 88.0 90.0
## GRAMD2B 83 88 93.0 91.0 84.0 90 87.0 92.0 85.0
## FOXE1 87 90 88.0 90.0 92.0 95 92.0 89.0 91.0
## ELFN1 80 85 89.0 92.0 87.0 88 88.0 93.0 88.0
## GABRA2 89 86 91.0 82.0 88.0 93 90.0 94.0 94.0
## ARG2 86 77 83.0 86.0 86.0 86 89.0 95.0 86.0
## TFCP2L1 75 79 74.0 87.0 72.0 33 83.0 80.0 74.0
## BARX1 82 80 81.0 83.0 81.0 87 86.0 82.0 89.0
## CLTRN 73 75 90.0 81.0 83.0 91 80.0 84.0 32.5
## PCOLCE2 85 83 67.0 71.0 82.0 77 76.0 85.0 77.0
## RASGRP1 79 66 75.0 80.0 31.5 83 82.0 73.0 76.0
## PLA1A 64 69 80.0 84.0 69.0 82 71.0 75.0 82.0
## COMP 71 74 85.0 32.5 31.5 75 74.0 78.0 32.5
## MPP1 66 78 87.0 76.0 85.0 72 84.0 83.0 87.0
## GLRA1 76 82 77.0 0.0 79.0 33 81.0 81.0 79.0
## GCNT4 0 81 68.0 68.0 65.0 84 79.0 0.0 0.0
## HCN4 70 0 84.0 88.0 0.0 33 32.5 87.0 81.0
## PRELP 84 31 65.0 32.5 71.0 33 32.5 33.5 0.0
## RHOT1 31 76 72.0 0.0 78.0 68 32.5 68.0 0.0
## MRO 0 0 76.0 0.0 64.0 79 85.0 0.0 80.0
## GAD1 74 31 32.5 32.5 75.0 81 32.5 33.5 75.0
## NTN1 67 0 0.0 85.0 31.5 33 0.0 72.0 32.5
## DACH2 77 0 71.0 79.0 76.0 0 0.0 0.0 0.0
## DCX 31 31 0.0 32.5 31.5 0 73.0 33.5 70.0
## ARL4C 65 31 32.5 0.0 66.0 70 65.0 33.5 73.0
## TBC1D4 0 0 79.0 75.0 67.0 0 78.0 76.0 0.0
## CPXM2 31 70 32.5 67.0 31.5 33 0.0 33.5 32.5
## FFAR4 63 0 32.5 32.5 77.0 0 72.0 74.0 71.0
## SLC24A2 31 31 0.0 32.5 31.5 33 70.0 33.5 32.5
## NOTUM 78 31 32.5 32.5 0.0 78 68.0 33.5 84.0
## LRRC2 31 31 32.5 0.0 31.5 33 32.5 33.5 32.5
## F11 31 31 0.0 0.0 31.5 0 32.5 33.5 0.0
## CMTR2 0 71 32.5 32.5 0.0 73 32.5 0.0 0.0
## LSAMP 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## CACNG5 31 31 0.0 32.5 31.5 33 32.5 33.5 32.5
## NIPAL4 31 31 0.0 32.5 31.5 0 32.5 33.5 32.5
## REEP1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## TAGLN3 0 0 70.0 73.0 0.0 0 0.0 69.0 0.0
## SERPINE2 81 0 0.0 0.0 31.5 0 0.0 33.5 66.0
## CLCF1 31 62 32.5 65.0 0.0 0 67.0 0.0 32.5
## C1QTNF1 72 65 69.0 0.0 0.0 0 32.5 67.0 69.0
## TSKU 62 72 32.5 77.0 31.5 69 0.0 0.0 0.0
## KCNA1 31 31 32.5 32.5 31.5 33 32.5 0.0 32.5
## SV2B 31 31 32.5 32.5 31.5 33 32.5 0.0 0.0
## CA5B 0 0 0.0 32.5 70.0 76 77.0 0.0 32.5
## FSTL4 0 31 0.0 32.5 0.0 33 32.5 0.0 32.5
## SIX6 68 0 78.0 32.5 80.0 71 0.0 0.0 67.0
## DKK3 31 31 32.5 0.0 31.5 33 32.5 33.5 32.5
## iter65 iter66 iter67 iter68 iter69 iter70 iter71 iter72 iter73
## OPRD1 93.0 93 97 92 93.0 97 87 98.0 86
## SLC2A2 89.0 87 91 91 91.0 96 86 96.0 89
## CHL1 92.0 89 92 90 92.0 95 85 93.0 90
## GRAMD2B 91.0 92 95 88 90.0 94 83 95.0 88
## FOXE1 94.0 91 94 93 94.0 93 84 94.0 91
## ELFN1 88.0 86 96 87 88.0 91 82 97.0 85
## GABRA2 90.0 88 93 86 83.0 87 81 84.0 87
## ARG2 79.0 90 85 84 89.0 92 76 85.0 76
## TFCP2L1 86.0 84 87 85 80.0 85 77 83.0 82
## BARX1 83.0 81 79 83 85.0 88 80 89.0 81
## CLTRN 87.0 83 73 80 87.0 90 72 82.0 68
## PCOLCE2 78.0 78 78 82 79.0 86 79 73.0 84
## RASGRP1 81.0 82 89 72 68.0 83 68 77.0 73
## PLA1A 82.0 79 70 73 78.0 89 78 92.0 77
## COMP 32.5 65 88 77 67.0 81 29 90.0 83
## MPP1 70.0 73 84 68 82.0 84 73 87.0 62
## GLRA1 77.0 68 82 69 76.0 70 0 0.0 78
## GCNT4 84.0 70 76 81 73.0 0 75 91.0 67
## HCN4 73.0 85 0 75 81.0 80 69 0.0 0
## PRELP 80.0 0 83 32 32.5 34 0 80.0 75
## RHOT1 32.5 76 34 70 75.0 79 29 86.0 0
## MRO 71.0 75 0 65 32.5 34 74 0.0 0
## GAD1 0.0 32 34 32 32.5 34 71 34.5 0
## NTN1 0.0 80 77 0 70.0 76 66 0.0 0
## DACH2 0.0 0 80 71 84.0 74 0 0.0 0
## DCX 68.0 0 34 89 86.0 0 29 34.5 0
## ARL4C 0.0 0 34 32 0.0 34 29 34.5 71
## TBC1D4 76.0 67 0 0 72.0 0 65 88.0 0
## CPXM2 66.0 0 34 32 32.5 73 29 74.0 31
## FFAR4 0.0 0 34 32 66.0 72 0 0.0 0
## SLC24A2 32.5 32 34 32 32.5 34 29 34.5 31
## NOTUM 32.5 32 0 32 32.5 34 59 34.5 31
## LRRC2 32.5 32 34 32 32.5 34 60 34.5 31
## F11 32.5 32 34 67 0.0 34 63 0.0 65
## CMTR2 67.0 32 0 0 0.0 68 0 81.0 0
## LSAMP 32.5 32 34 32 32.5 34 29 34.5 31
## CACNG5 32.5 32 34 32 32.5 34 29 34.5 31
## NIPAL4 32.5 0 34 32 32.5 75 29 34.5 80
## REEP1 32.5 32 0 32 32.5 34 29 34.5 31
## TAGLN3 75.0 74 90 0 0.0 78 0 78.0 31
## SERPINE2 32.5 32 71 32 32.5 0 29 0.0 70
## CLCF1 32.5 0 34 0 32.5 71 0 69.0 66
## C1QTNF1 0.0 0 69 0 0.0 34 0 0.0 64
## TSKU 65.0 32 0 79 32.5 0 0 79.0 0
## KCNA1 32.5 32 34 32 32.5 34 29 34.5 31
## SV2B 32.5 32 34 32 32.5 34 29 34.5 31
## CA5B 32.5 0 0 32 32.5 0 64 0.0 79
## FSTL4 32.5 32 34 32 32.5 34 29 34.5 31
## SIX6 0.0 32 0 0 0.0 0 0 0.0 0
## DKK3 32.5 32 0 32 32.5 34 0 34.5 31
## iter74 iter75 iter76 iter77 iter78 iter79 iter80 iter81 iter82
## OPRD1 90.0 94.0 94 95 93.0 96.0 93.0 95 94.0
## SLC2A2 88.0 90.0 95 94 92.0 97.0 87.0 91 93.0
## CHL1 85.0 84.0 92 90 91.0 95.0 92.0 92 92.0
## GRAMD2B 86.0 89.0 87 88 89.0 93.0 91.0 88 88.0
## FOXE1 89.0 92.0 91 89 94.0 98.0 90.0 93 91.0
## ELFN1 87.0 91.0 88 91 90.0 90.0 82.0 90 89.0
## GABRA2 80.0 85.0 93 93 87.0 92.0 86.0 94 90.0
## ARG2 71.0 77.0 85 86 86.0 74.0 89.0 87 78.0
## TFCP2L1 82.0 32.5 70 85 74.0 76.0 94.0 81 84.0
## BARX1 81.0 79.0 90 92 88.0 88.0 0.0 86 87.0
## CLTRN 65.0 73.0 78 87 80.0 86.0 32.5 84 72.0
## PCOLCE2 62.0 72.0 79 83 85.0 89.0 83.0 76 76.0
## RASGRP1 78.0 93.0 80 80 72.0 85.0 0.0 73 81.0
## PLA1A 30.5 68.0 86 84 79.0 94.0 32.5 33 32.5
## COMP 77.0 87.0 33 75 0.0 79.0 84.0 74 80.0
## MPP1 30.5 0.0 89 73 75.0 91.0 65.0 82 82.0
## GLRA1 79.0 74.0 82 78 83.0 82.0 32.5 78 83.0
## GCNT4 84.0 75.0 33 77 84.0 0.0 32.5 33 86.0
## HCN4 66.0 0.0 75 81 69.0 72.0 88.0 75 66.0
## PRELP 30.5 67.0 33 74 66.0 83.0 32.5 33 74.0
## RHOT1 30.5 80.0 33 0 32.5 0.0 0.0 0 69.0
## MRO 61.0 32.5 84 79 0.0 0.0 0.0 33 79.0
## GAD1 30.5 32.5 74 33 32.5 0.0 32.5 67 32.5
## NTN1 74.0 0.0 33 76 0.0 0.0 85.0 79 32.5
## DACH2 76.0 78.0 77 0 81.0 34.5 0.0 83 85.0
## DCX 75.0 86.0 33 0 0.0 0.0 0.0 70 0.0
## ARL4C 30.5 81.0 69 33 0.0 75.0 32.5 33 70.0
## TBC1D4 70.0 83.0 73 0 0.0 0.0 0.0 71 0.0
## CPXM2 72.0 32.5 33 33 32.5 34.5 0.0 33 67.0
## FFAR4 0.0 32.5 81 72 76.0 81.0 32.5 85 32.5
## SLC24A2 30.5 32.5 33 33 32.5 34.5 32.5 68 32.5
## NOTUM 0.0 0.0 33 68 70.0 34.5 0.0 33 32.5
## LRRC2 30.5 65.0 33 33 32.5 34.5 32.5 33 32.5
## F11 83.0 32.5 0 33 0.0 34.5 32.5 69 0.0
## CMTR2 63.0 0.0 0 71 32.5 0.0 71.0 0 65.0
## LSAMP 30.5 32.5 33 33 32.5 34.5 0.0 33 32.5
## CACNG5 30.5 32.5 0 33 32.5 0.0 32.5 33 32.5
## NIPAL4 30.5 0.0 33 66 0.0 84.0 32.5 0 32.5
## REEP1 30.5 32.5 33 33 32.5 34.5 0.0 33 32.5
## TAGLN3 0.0 0.0 33 69 0.0 34.5 0.0 80 0.0
## SERPINE2 69.0 82.0 0 0 0.0 0.0 68.0 33 32.5
## CLCF1 30.5 32.5 0 0 0.0 0.0 66.0 0 0.0
## C1QTNF1 0.0 76.0 33 33 0.0 69.0 0.0 33 32.5
## TSKU 0.0 32.5 33 33 0.0 0.0 74.0 33 32.5
## KCNA1 30.5 32.5 0 33 32.5 0.0 32.5 33 32.5
## SV2B 30.5 0.0 0 33 32.5 0.0 0.0 72 32.5
## CA5B 30.5 0.0 0 33 71.0 0.0 0.0 0 32.5
## FSTL4 30.5 32.5 33 33 32.5 34.5 0.0 33 32.5
## SIX6 0.0 32.5 83 70 0.0 77.0 0.0 89 0.0
## DKK3 0.0 32.5 33 33 32.5 34.5 0.0 33 32.5
## iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90 iter91
## OPRD1 98.0 98.0 92 96.0 91 94.0 93 95 95.0
## SLC2A2 94.0 94.0 90 91.0 89 90.0 92 92 90.0
## CHL1 97.0 92.0 91 94.0 87 92.0 91 79 96.0
## GRAMD2B 95.0 96.0 86 87.0 90 87.0 86 94 92.0
## FOXE1 96.0 97.0 93 92.0 88 91.0 88 0 91.0
## ELFN1 91.0 95.0 88 88.0 93 89.0 90 97 88.0
## GABRA2 93.0 77.0 89 95.0 74 84.0 87 93 94.0
## ARG2 88.0 82.0 84 86.0 86 83.0 82 90 87.0
## TFCP2L1 80.0 91.0 79 93.0 0 86.0 76 84 81.0
## BARX1 72.0 74.0 85 83.0 32 78.0 83 82 78.0
## CLTRN 71.0 90.0 72 89.0 84 88.0 84 86 84.0
## PCOLCE2 84.0 89.0 75 78.0 85 93.0 85 77 83.0
## RASGRP1 77.0 93.0 82 79.0 0 76.0 79 0 93.0
## PLA1A 83.0 78.0 81 90.0 65 73.0 89 91 89.0
## COMP 92.0 73.0 32 71.0 92 85.0 71 89 73.0
## MPP1 76.0 0.0 80 82.0 0 66.0 81 0 0.0
## GLRA1 0.0 0.0 87 75.0 0 74.0 75 0 76.0
## GCNT4 34.5 76.0 64 72.0 70 68.0 65 74 68.0
## HCN4 89.0 70.0 32 84.0 0 82.0 69 80 33.5
## PRELP 34.5 34.5 32 33.5 73 77.0 32 88 79.0
## RHOT1 73.0 84.0 32 68.0 32 75.0 72 73 86.0
## MRO 0.0 87.0 32 85.0 0 81.0 68 70 0.0
## GAD1 34.5 34.5 0 33.5 71 32.5 77 34 80.0
## NTN1 82.0 0.0 32 77.0 0 79.0 64 0 0.0
## DACH2 90.0 80.0 78 0.0 0 0.0 0 0 85.0
## DCX 78.0 88.0 73 69.0 82 0.0 0 0 33.5
## ARL4C 34.5 34.5 32 33.5 0 0.0 70 34 74.0
## TBC1D4 75.0 75.0 0 81.0 0 0.0 0 81 0.0
## CPXM2 34.5 81.0 32 0.0 0 69.0 32 34 33.5
## FFAR4 34.5 0.0 83 0.0 0 0.0 73 0 82.0
## SLC24A2 0.0 34.5 32 33.5 32 32.5 32 34 33.5
## NOTUM 0.0 34.5 68 33.5 0 72.0 32 0 33.5
## LRRC2 34.5 79.0 0 33.5 75 32.5 32 34 33.5
## F11 34.5 34.5 32 33.5 83 32.5 0 0 33.5
## CMTR2 0.0 34.5 0 70.0 0 80.0 32 96 33.5
## LSAMP 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## CACNG5 34.5 34.5 0 33.5 32 32.5 74 34 33.5
## NIPAL4 34.5 0.0 32 33.5 67 0.0 80 0 33.5
## REEP1 34.5 34.5 32 33.5 32 0.0 32 34 33.5
## TAGLN3 69.0 72.0 71 80.0 0 32.5 0 0 0.0
## SERPINE2 34.5 34.5 0 0.0 32 70.0 32 0 70.0
## CLCF1 0.0 0.0 0 33.5 72 0.0 0 78 75.0
## C1QTNF1 0.0 34.5 32 0.0 0 0.0 32 83 72.0
## TSKU 70.0 0.0 0 33.5 0 71.0 0 34 0.0
## KCNA1 34.5 34.5 32 33.5 32 32.5 0 34 33.5
## SV2B 0.0 34.5 32 33.5 32 32.5 32 0 0.0
## CA5B 34.5 34.5 32 0.0 81 32.5 32 0 0.0
## FSTL4 0.0 34.5 32 33.5 32 32.5 0 0 33.5
## SIX6 34.5 0.0 77 0.0 0 0.0 32 0 69.0
## DKK3 34.5 34.5 32 33.5 0 32.5 32 34 33.5
## iter92 iter93 iter94 iter95 iter96 iter97 iter98 iter99 iter100
## OPRD1 90 89 96.0 90.0 91.0 91.0 96.0 96.0 89.0
## SLC2A2 92 88 90.0 89.0 86.0 87.0 76.0 91.0 92.0
## CHL1 91 91 91.0 86.0 89.0 89.0 91.0 88.0 90.0
## GRAMD2B 88 84 95.0 82.0 90.0 90.0 94.0 92.0 85.0
## FOXE1 93 90 87.0 88.0 92.0 92.0 92.0 94.0 91.0
## ELFN1 86 85 92.0 87.0 85.0 88.0 93.0 84.0 81.0
## GABRA2 89 87 94.0 85.0 87.0 85.0 85.0 90.0 88.0
## ARG2 75 81 89.0 79.0 88.0 84.0 95.0 95.0 71.0
## TFCP2L1 84 78 93.0 78.0 69.0 86.0 77.0 93.0 75.0
## BARX1 85 86 0.0 83.0 31.5 31.5 68.0 73.0 86.0
## CLTRN 79 76 0.0 84.0 70.0 67.0 69.0 70.0 82.0
## PCOLCE2 76 80 69.0 81.0 31.5 83.0 33.5 69.0 31.5
## RASGRP1 0 82 75.0 62.0 67.0 66.0 0.0 82.0 72.0
## PLA1A 69 73 0.0 69.0 83.0 77.0 33.5 80.0 73.0
## COMP 82 31 84.0 61.0 72.0 74.0 78.0 33.5 31.5
## MPP1 71 68 0.0 70.0 68.0 82.0 0.0 83.0 78.0
## GLRA1 83 77 0.0 76.0 82.0 0.0 0.0 85.0 87.0
## GCNT4 87 69 79.0 66.0 77.0 65.0 70.0 33.5 74.0
## HCN4 32 66 86.0 75.0 76.0 0.0 90.0 87.0 83.0
## PRELP 0 72 85.0 30.5 31.5 31.5 0.0 33.5 31.5
## RHOT1 72 0 77.0 0.0 75.0 75.0 88.0 33.5 31.5
## MRO 80 0 0.0 73.0 66.0 78.0 82.0 86.0 64.0
## GAD1 0 75 33.5 77.0 31.5 31.5 33.5 33.5 66.0
## NTN1 32 31 0.0 30.5 0.0 73.0 79.0 89.0 31.5
## DACH2 77 74 0.0 0.0 81.0 0.0 0.0 0.0 84.0
## DCX 81 70 0.0 30.5 84.0 81.0 83.0 76.0 31.5
## ARL4C 32 71 33.5 64.0 0.0 31.5 0.0 33.5 0.0
## TBC1D4 74 0 0.0 0.0 64.0 76.0 0.0 77.0 63.0
## CPXM2 32 31 80.0 30.5 31.5 70.0 0.0 0.0 31.5
## FFAR4 0 67 0.0 0.0 0.0 0.0 33.5 81.0 65.0
## SLC24A2 32 31 33.5 30.5 31.5 31.5 33.5 33.5 0.0
## NOTUM 32 31 0.0 80.0 31.5 0.0 0.0 75.0 31.5
## LRRC2 32 31 33.5 30.5 31.5 69.0 75.0 33.5 31.5
## F11 32 83 0.0 67.0 31.5 79.0 0.0 0.0 31.5
## CMTR2 32 0 88.0 0.0 31.5 0.0 71.0 67.0 0.0
## LSAMP 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## CACNG5 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## NIPAL4 32 31 33.5 30.5 0.0 31.5 0.0 33.5 31.5
## REEP1 32 31 33.5 0.0 31.5 0.0 33.5 33.5 31.5
## TAGLN3 0 65 0.0 0.0 31.5 0.0 0.0 72.0 0.0
## SERPINE2 32 63 0.0 30.5 0.0 71.0 0.0 0.0 0.0
## CLCF1 32 31 33.5 0.0 31.5 0.0 33.5 33.5 0.0
## C1QTNF1 0 0 68.0 0.0 0.0 0.0 0.0 33.5 0.0
## TSKU 32 0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
## KCNA1 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## SV2B 65 31 0.0 30.5 31.5 31.5 33.5 33.5 31.5
## CA5B 73 31 73.0 30.5 73.0 68.0 74.0 0.0 0.0
## FSTL4 32 31 33.5 30.5 31.5 0.0 33.5 33.5 31.5
## SIX6 0 64 0.0 72.0 0.0 31.5 33.5 0.0 31.5
## DKK3 32 31 0.0 30.5 31.5 0.0 0.0 0.0 31.5
## total_rank
## OPRD1 9339.0
## SLC2A2 9078.0
## CHL1 9010.0
## GRAMD2B 8965.0
## FOXE1 8961.0
## ELFN1 8834.0
## GABRA2 8815.0
## ARG2 8426.0
## TFCP2L1 7681.0
## BARX1 7578.0
## CLTRN 7467.0
## PCOLCE2 7353.5
## RASGRP1 7053.0
## PLA1A 6902.5
## COMP 6566.0
## MPP1 6549.5
## GLRA1 6162.5
## GCNT4 5905.0
## HCN4 5878.0
## PRELP 4914.5
## RHOT1 4506.0
## MRO 4381.5
## GAD1 4366.5
## NTN1 4223.0
## DACH2 4060.5
## DCX 4030.5
## ARL4C 3900.0
## TBC1D4 3716.0
## CPXM2 3596.5
## FFAR4 3555.5
## SLC24A2 3395.5
## NOTUM 3341.5
## LRRC2 3318.0
## F11 3260.0
## CMTR2 3231.0
## LSAMP 3193.5
## CACNG5 2974.5
## NIPAL4 2966.0
## REEP1 2966.0
## TAGLN3 2918.5
## SERPINE2 2881.5
## CLCF1 2803.5
## C1QTNF1 2791.0
## TSKU 2782.5
## KCNA1 2765.0
## SV2B 2676.0
## CA5B 2670.5
## FSTL4 2638.5
## SIX6 2615.0
## DKK3 2609.0write.table(expr_features_comp1_final,file="Comp1_EXPR_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
expr_features_comp2_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),expr_features_comp2)
rownames(expr_features_comp2_final)<-expr_features_comp2_final$GENE
expr_features_comp2_final$GENE<-NULL
expr_features_comp2_final[is.na(expr_features_comp2_final)]<-0
expr_features_comp2_final$total_rank<-rowSums(expr_features_comp2_final)
expr_features_comp2_final<-expr_features_comp2_final[order(-expr_features_comp2_final$total_rank),]
print(head(expr_features_comp2_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10
## LSAMP 82 90.0 88.0 84 91.0 66 83.0 86 77.0 78.0
## REEP1 86 93.0 93.0 83 96.0 90 87.0 90 83.0 83.0
## CACNG5 92 92.0 0.0 93 0.0 74 95.0 91 86.0 91.0
## FSTL4 83 87.0 92.0 81 0.0 0 89.0 89 75.0 79.0
## SLC24A2 80 80.0 70.0 33 69.0 68 85.0 73 31.5 74.0
## CNTN5 0 89.0 0.0 73 76.0 32 80.0 79 72.0 73.0
## KCNA1 73 88.0 91.0 33 0.0 0 78.0 81 65.0 67.0
## PCOLCE2 75 32.5 85.0 70 79.0 32 77.0 32 31.5 33.5
## NOTUM 69 91.0 0.0 68 86.0 0 0.0 32 79.0 0.0
## GNAL 91 0.0 94.0 88 95.0 86 86.0 0 0.0 88.0
## NEFL 0 66.0 86.0 86 83.0 32 0.0 70 64.0 0.0
## SULF1 0 0.0 89.0 77 94.0 92 0.0 0 78.0 0.0
## TIAM1 0 0.0 0.0 92 0.0 0 96.0 93 90.0 93.0
## NXPH3 93 0.0 0.0 90 0.0 0 93.0 0 0.0 94.0
## GAD1 71 32.5 79.0 71 33.5 32 72.0 0 31.5 33.5
## TSHR 84 0.0 0.0 85 0.0 0 88.0 84 68.0 85.0
## DKK3 0 32.5 82.0 33 82.0 80 33.5 32 31.5 33.5
## ELFN1 32 32.5 69.0 33 68.0 32 71.0 32 31.5 33.5
## SHISAL1 0 0.0 0.0 95 0.0 0 0.0 92 89.0 92.0
## ARL4C 74 72.0 0.0 33 75.0 32 68.0 66 31.5 33.5
## PTCHD4 0 0.0 0.0 87 93.0 0 0.0 0 84.0 0.0
## SFTPA1 0 0.0 0.0 82 0.0 0 90.0 0 81.0 80.0
## BARX1 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## ARG2 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## CHL1 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## GABRA2 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## GRAMD2B 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## OPRD1 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## SLC2A2 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## CPXM2 0 32.5 32.5 33 33.5 32 0.0 32 31.5 0.0
## COMP 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## TFCP2L1 32 32.5 32.5 33 33.5 0 33.5 32 31.5 33.5
## FOXE1 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## PLA1A 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## CLTRN 0 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## NIPAL4 77 69.0 0.0 0 0.0 32 79.0 64 31.5 0.0
## SYT1 0 0.0 0.0 0 0.0 0 91.0 83 76.0 90.0
## RASGRP1 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## KIAA0319 0 0.0 0.0 0 0.0 0 0.0 0 92.0 96.0
## FSTL5 0 0.0 0.0 72 81.0 0 0.0 0 0.0 0.0
## PRELP 0 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## LRRC2 32 0.0 0.0 33 0.0 79 0.0 32 31.5 33.5
## SV2B 32 32.5 32.5 33 33.5 0 33.5 67 0.0 33.5
## F11 0 32.5 0.0 0 0.0 65 0.0 32 31.5 33.5
## GLRA1 32 77.0 65.0 33 33.5 32 0.0 32 31.5 0.0
## CTSZ 0 0.0 74.0 0 87.0 77 0.0 0 0.0 0.0
## GCNT4 32 32.5 32.5 33 33.5 32 33.5 32 31.5 33.5
## MPP1 32 32.5 32.5 33 33.5 32 33.5 0 31.5 33.5
## HCN4 32 32.5 32.5 33 33.5 32 33.5 32 0.0 33.5
## LRRTM2 0 94.0 0.0 75 0.0 84 0.0 78 0.0 0.0
## iter11 iter12 iter13 iter14 iter15 iter16 iter17 iter18 iter19
## LSAMP 83.0 84 90 86 84 82 88.0 87 85
## REEP1 90.0 89 0 90 0 84 94.0 88 93
## CACNG5 87.0 91 93 88 89 88 92.0 93 0
## FSTL4 81.0 0 88 74 0 80 79.0 73 94
## SLC24A2 68.0 80 33 67 31 71 73.0 78 84
## CNTN5 80.0 0 0 80 0 78 80.0 69 88
## KCNA1 78.0 0 0 66 85 66 76.0 34 72
## PCOLCE2 32.5 69 72 73 71 70 75.0 34 34
## NOTUM 82.0 0 0 64 76 0 74.0 81 82
## GNAL 0.0 95 0 89 0 0 0.0 92 83
## NEFL 77.0 0 86 81 0 0 89.0 0 86
## SULF1 86.0 0 0 83 0 0 91.0 94 91
## TIAM1 93.0 0 0 0 91 91 96.0 97 0
## NXPH3 0.0 94 0 0 0 90 95.0 0 0
## GAD1 71.0 33 68 32 72 69 0.0 34 34
## TSHR 0.0 82 0 0 63 72 0.0 77 0
## DKK3 32.5 0 75 68 0 0 34.5 71 34
## ELFN1 32.5 33 33 32 74 32 34.5 34 34
## SHISAL1 0.0 0 0 0 90 92 0.0 95 0
## ARL4C 32.5 33 69 32 65 79 34.5 34 34
## PTCHD4 89.0 0 0 0 0 0 90.0 91 87
## SFTPA1 91.0 0 0 0 0 0 93.0 0 95
## BARX1 32.5 33 33 32 31 32 34.5 34 34
## ARG2 32.5 33 33 32 31 32 34.5 34 34
## CHL1 32.5 33 33 32 31 32 34.5 34 34
## GABRA2 32.5 33 33 32 31 32 34.5 34 34
## GRAMD2B 32.5 33 33 32 31 32 34.5 34 34
## OPRD1 32.5 33 33 32 31 32 34.5 34 34
## SLC2A2 32.5 33 33 32 31 32 34.5 34 34
## CPXM2 32.5 33 33 32 31 32 34.5 34 34
## COMP 32.5 33 33 32 31 32 34.5 34 34
## TFCP2L1 32.5 33 33 32 31 32 34.5 34 34
## FOXE1 32.5 33 33 32 31 32 34.5 34 34
## PLA1A 32.5 33 33 32 31 32 34.5 34 34
## CLTRN 32.5 33 33 32 31 0 34.5 34 34
## NIPAL4 32.5 71 33 32 31 77 34.5 34 34
## SYT1 0.0 92 0 0 88 0 0.0 82 0
## RASGRP1 32.5 33 33 32 31 32 34.5 34 34
## KIAA0319 94.0 0 0 0 0 93 98.0 96 0
## FSTL5 79.0 0 0 82 0 0 85.0 0 0
## PRELP 32.5 0 33 32 0 32 34.5 34 34
## LRRC2 32.5 33 0 32 31 32 34.5 34 34
## SV2B 32.5 67 0 32 31 0 34.5 34 34
## F11 67.0 68 33 32 31 32 34.5 0 34
## GLRA1 32.5 0 0 32 31 32 34.5 34 0
## CTSZ 76.0 0 0 79 0 0 81.0 0 89
## GCNT4 32.5 33 0 32 31 32 34.5 34 34
## MPP1 0.0 0 33 32 31 32 34.5 34 34
## HCN4 0.0 33 33 32 31 32 0.0 34 0
## LRRTM2 84.0 0 0 85 0 75 0.0 0 0
## iter20 iter21 iter22 iter23 iter24 iter25 iter26 iter27 iter28
## LSAMP 84.0 82.0 83.0 85 93.0 78.0 80 90 0.0
## REEP1 82.0 86.0 86.0 0 92.0 82.0 94 92 92.0
## CACNG5 90.0 81.0 84.0 94 91.0 81.0 0 91 0.0
## FSTL4 80.0 79.0 85.0 0 94.0 76.0 0 0 76.0
## SLC24A2 67.0 84.0 78.0 74 69.0 65.0 73 80 31.5
## CNTN5 78.0 77.0 79.0 84 83.0 70.0 0 0 0.0
## KCNA1 30.5 66.0 32.5 86 75.0 75.0 0 0 85.0
## PCOLCE2 70.0 32.5 32.5 76 33.5 31.5 33 71 31.5
## NOTUM 75.0 78.0 66.0 89 33.5 66.0 0 85 79.0
## GNAL 86.0 73.0 91.0 0 0.0 84.0 0 93 0.0
## NEFL 68.0 70.0 80.0 71 84.0 67.0 0 86 80.0
## SULF1 77.0 85.0 74.0 90 74.0 80.0 91 88 88.0
## TIAM1 0.0 0.0 88.0 97 0.0 88.0 0 0 0.0
## NXPH3 87.0 87.0 92.0 0 95.0 90.0 0 0 0.0
## GAD1 30.5 65.0 32.5 34 71.0 31.5 33 79 78.0
## TSHR 0.0 0.0 75.0 87 0.0 74.0 0 0 0.0
## DKK3 66.0 72.0 32.5 34 72.0 31.5 85 75 77.0
## ELFN1 30.5 32.5 32.5 34 33.5 31.5 33 73 31.5
## SHISAL1 0.0 0.0 93.0 0 0.0 87.0 0 0 0.0
## ARL4C 30.5 32.5 32.5 34 33.5 31.5 33 76 31.5
## PTCHD4 89.0 89.0 0.0 0 82.0 0.0 0 0 0.0
## SFTPA1 85.0 91.0 89.0 0 90.0 86.0 0 0 87.0
## BARX1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## ARG2 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## CHL1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## GABRA2 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## GRAMD2B 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## OPRD1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## SLC2A2 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## CPXM2 30.5 32.5 32.5 34 33.5 31.5 76 81 68.0
## COMP 30.5 32.5 32.5 34 33.5 31.5 33 0 31.5
## TFCP2L1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## FOXE1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## PLA1A 30.5 32.5 32.5 34 33.5 31.5 33 0 31.5
## CLTRN 30.5 32.5 32.5 34 33.5 31.5 0 32 31.5
## NIPAL4 0.0 32.5 32.5 72 33.5 31.5 33 83 31.5
## SYT1 0.0 0.0 73.0 0 0.0 77.0 0 0 0.0
## RASGRP1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## KIAA0319 0.0 0.0 94.0 0 0.0 91.0 0 0 0.0
## FSTL5 0.0 80.0 0.0 75 78.0 73.0 0 87 0.0
## PRELP 30.5 32.5 0.0 34 33.5 31.5 33 32 31.5
## LRRC2 0.0 32.5 32.5 34 33.5 31.5 0 32 31.5
## SV2B 30.5 32.5 32.5 34 0.0 31.5 0 32 0.0
## F11 0.0 0.0 65.0 0 33.5 31.5 33 78 66.0
## GLRA1 30.5 32.5 32.5 34 33.5 31.5 33 32 69.0
## CTSZ 0.0 71.0 0.0 0 79.0 0.0 74 0 64.0
## GCNT4 30.5 32.5 32.5 34 0.0 31.5 33 32 31.5
## MPP1 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## HCN4 30.5 32.5 32.5 34 33.5 31.5 33 32 31.5
## LRRTM2 0.0 88.0 0.0 83 0.0 79.0 0 0 0.0
## iter29 iter30 iter31 iter32 iter33 iter34 iter35 iter36 iter37
## LSAMP 77 93 82 80.0 87.0 83 91.0 86.0 84
## REEP1 87 91 91 87.0 90.0 87 80.0 88.0 93
## CACNG5 88 95 92 89.0 89.0 88 94.0 90.0 82
## FSTL4 78 87 90 81.0 85.0 85 72.0 85.0 81
## SLC24A2 65 76 80 76.0 79.0 71 34.5 70.0 80
## CNTN5 74 81 84 68.0 80.0 81 76.0 84.0 0
## KCNA1 70 0 81 71.0 71.0 80 86.0 33.5 67
## PCOLCE2 66 69 33 65.0 78.0 64 34.5 33.5 32
## NOTUM 81 33 74 0.0 74.0 74 0.0 81.0 77
## GNAL 83 0 0 91.0 91.0 89 0.0 0.0 92
## NEFL 69 82 33 0.0 72.0 77 0.0 72.0 70
## SULF1 0 75 77 0.0 0.0 79 0.0 80.0 91
## TIAM1 0 0 0 92.0 92.0 91 92.0 0.0 0
## NXPH3 91 92 93 0.0 0.0 90 96.0 0.0 0
## GAD1 72 33 72 75.0 0.0 69 34.5 33.5 32
## TSHR 79 88 0 79.0 83.0 72 77.0 71.0 0
## DKK3 0 33 33 0.0 31.5 32 34.5 33.5 71
## ELFN1 32 33 33 72.0 63.0 32 34.5 33.5 32
## SHISAL1 92 0 95 93.0 0.0 93 97.0 94.0 0
## ARL4C 32 33 33 0.0 77.0 32 34.5 0.0 32
## PTCHD4 0 84 83 0.0 0.0 0 74.0 91.0 89
## SFTPA1 0 0 0 0.0 0.0 84 0.0 92.0 90
## BARX1 32 33 33 66.0 31.5 32 34.5 33.5 32
## ARG2 32 33 33 32.5 31.5 32 34.5 33.5 32
## CHL1 32 33 33 32.5 31.5 32 34.5 33.5 32
## GABRA2 32 33 33 32.5 31.5 32 34.5 33.5 32
## GRAMD2B 32 33 33 32.5 31.5 32 34.5 33.5 32
## OPRD1 32 33 33 32.5 31.5 32 34.5 33.5 32
## SLC2A2 32 33 33 32.5 31.5 32 34.5 33.5 32
## CPXM2 32 33 33 32.5 31.5 32 0.0 0.0 66
## COMP 32 33 33 32.5 31.5 32 34.5 33.5 32
## TFCP2L1 32 33 0 32.5 31.5 32 34.5 33.5 32
## FOXE1 32 33 33 32.5 31.5 32 34.5 33.5 32
## PLA1A 32 33 33 32.5 31.5 32 34.5 33.5 32
## CLTRN 32 33 33 32.5 31.5 32 34.5 33.5 32
## NIPAL4 0 0 33 0.0 0.0 32 0.0 0.0 32
## SYT1 0 0 0 90.0 88.0 0 34.5 0.0 0
## RASGRP1 32 33 0 32.5 31.5 32 0.0 33.5 32
## KIAA0319 93 0 0 94.0 0.0 0 98.0 96.0 0
## FSTL5 85 79 0 0.0 0.0 0 84.0 79.0 85
## PRELP 32 33 33 32.5 31.5 32 34.5 33.5 32
## LRRC2 32 33 0 32.5 31.5 32 34.5 33.5 0
## SV2B 32 33 33 32.5 31.5 32 0.0 33.5 32
## F11 32 33 33 69.0 31.5 0 0.0 0.0 32
## GLRA1 32 33 0 32.5 31.5 0 34.5 33.5 0
## CTSZ 0 33 0 0.0 0.0 66 0.0 69.0 88
## GCNT4 32 33 33 32.5 31.5 32 0.0 33.5 0
## MPP1 32 33 0 32.5 0.0 32 34.5 33.5 32
## HCN4 0 0 33 32.5 31.5 32 34.5 33.5 32
## LRRTM2 86 73 87 0.0 76.0 0 82.0 0.0 0
## iter38 iter39 iter40 iter41 iter42 iter43 iter44 iter45 iter46
## LSAMP 80 80.0 81 72.0 77 87.0 83.0 90 69
## REEP1 71 88.0 85 91.0 86 89.0 0.0 91 86
## CACNG5 90 90.0 82 85.0 83 82.0 92.0 92 83
## FSTL4 34 78.0 79 78.0 74 79.0 84.0 87 70
## SLC24A2 34 32.5 30 32.5 72 85.0 78.0 85 34
## CNTN5 34 75.0 74 79.0 0 77.0 81.0 75 74
## KCNA1 0 83.0 72 32.5 0 81.0 32.5 71 71
## PCOLCE2 34 67.0 75 32.5 32 32.5 32.5 72 34
## NOTUM 0 69.0 0 67.0 65 76.0 79.0 74 0
## GNAL 96 86.0 89 0.0 90 93.0 0.0 0 89
## NEFL 0 73.0 0 81.0 78 78.0 0.0 84 72
## SULF1 75 0.0 0 0.0 0 86.0 0.0 78 0
## TIAM1 93 93.0 0 89.0 91 0.0 94.0 0 90
## NXPH3 89 0.0 88 90.0 89 94.0 0.0 0 95
## GAD1 81 32.5 65 32.5 32 66.0 72.0 33 34
## TSHR 87 74.0 71 65.0 82 73.0 87.0 0 88
## DKK3 34 32.5 61 32.5 0 83.0 0.0 33 0
## ELFN1 34 32.5 30 32.5 32 71.0 32.5 33 34
## SHISAL1 95 0.0 0 93.0 88 90.0 93.0 0 92
## ARL4C 34 32.5 78 32.5 32 68.0 74.0 73 0
## PTCHD4 0 0.0 0 84.0 0 0.0 0.0 0 0
## SFTPA1 0 87.0 0 0.0 0 88.0 0.0 0 0
## BARX1 34 32.5 30 32.5 32 32.5 0.0 33 34
## ARG2 34 32.5 30 32.5 32 32.5 32.5 33 34
## CHL1 34 32.5 30 32.5 32 32.5 32.5 33 34
## GABRA2 34 32.5 30 32.5 32 32.5 32.5 33 34
## GRAMD2B 34 32.5 30 32.5 32 32.5 32.5 33 34
## OPRD1 34 32.5 30 32.5 32 32.5 32.5 33 34
## SLC2A2 34 32.5 30 32.5 32 32.5 32.5 33 34
## CPXM2 0 32.5 30 32.5 32 70.0 32.5 33 34
## COMP 34 32.5 30 32.5 32 65.0 32.5 33 0
## TFCP2L1 34 32.5 30 32.5 32 32.5 32.5 33 34
## FOXE1 34 32.5 30 32.5 32 32.5 0.0 33 34
## PLA1A 34 32.5 30 32.5 32 32.5 0.0 33 34
## CLTRN 34 32.5 30 32.5 32 32.5 0.0 33 34
## NIPAL4 0 32.5 62 0.0 32 0.0 67.0 33 0
## SYT1 84 0.0 0 0.0 84 84.0 89.0 0 78
## RASGRP1 34 32.5 30 32.5 0 32.5 32.5 33 34
## KIAA0319 94 0.0 0 0.0 93 0.0 0.0 0 97
## FSTL5 73 0.0 0 83.0 0 0.0 0.0 0 82
## PRELP 34 32.5 0 32.5 32 32.5 32.5 33 34
## LRRC2 0 32.5 30 0.0 32 32.5 32.5 33 34
## SV2B 34 32.5 30 0.0 32 74.0 0.0 33 0
## F11 0 66.0 30 32.5 32 32.5 0.0 33 0
## GLRA1 34 32.5 63 32.5 0 32.5 32.5 33 0
## CTSZ 0 81.0 0 0.0 0 0.0 0.0 83 0
## GCNT4 0 32.5 30 32.5 32 32.5 32.5 33 34
## MPP1 34 32.5 30 32.5 0 32.5 0.0 33 34
## HCN4 34 32.5 0 32.5 0 32.5 32.5 33 34
## LRRTM2 74 85.0 0 86.0 0 0.0 77.0 88 75
## iter47 iter48 iter49 iter50 iter51 iter52 iter53 iter54 iter55
## LSAMP 86.0 80.0 90.0 82 86.0 66 89 81 79
## REEP1 87.0 91.0 95.0 90 91.0 89 90 92 82
## CACNG5 92.0 90.0 0.0 0 88.0 88 94 95 77
## FSTL4 81.0 0.0 91.0 81 87.0 0 0 88 70
## SLC24A2 78.0 77.0 84.0 74 85.0 77 76 82 31
## CNTN5 77.0 0.0 88.0 0 0.0 0 85 80 75
## KCNA1 32.5 81.0 87.0 0 82.0 0 34 89 63
## PCOLCE2 74.0 67.0 81.0 84 72.0 69 75 35 31
## NOTUM 67.0 79.0 69.0 80 79.0 75 83 75 68
## GNAL 89.0 94.0 0.0 0 92.0 91 91 96 0
## NEFL 85.0 0.0 83.0 33 74.0 0 0 0 31
## SULF1 83.0 87.0 82.0 83 89.0 0 0 0 78
## TIAM1 93.0 93.0 0.0 0 0.0 0 97 0 87
## NXPH3 88.0 92.0 0.0 0 0.0 0 0 98 85
## GAD1 72.0 66.0 0.0 33 76.0 65 34 74 31
## TSHR 79.0 82.0 0.0 0 0.0 0 82 0 0
## DKK3 32.5 32.5 34.5 76 75.0 74 72 0 31
## ELFN1 32.5 75.0 34.5 33 31.5 68 34 35 31
## SHISAL1 0.0 0.0 0.0 0 0.0 0 0 90 86
## ARL4C 32.5 32.5 70.0 33 0.0 0 34 0 31
## PTCHD4 0.0 88.0 92.0 85 0.0 0 92 0 84
## SFTPA1 0.0 0.0 94.0 0 90.0 0 96 0 88
## BARX1 32.5 32.5 34.5 33 31.5 31 34 35 31
## ARG2 32.5 32.5 34.5 33 31.5 31 34 35 31
## CHL1 32.5 32.5 34.5 33 31.5 31 34 35 31
## GABRA2 32.5 32.5 34.5 33 31.5 31 34 35 31
## GRAMD2B 32.5 32.5 34.5 33 31.5 31 34 35 31
## OPRD1 32.5 32.5 34.5 33 31.5 31 34 35 31
## SLC2A2 32.5 32.5 34.5 33 31.5 31 34 35 31
## CPXM2 32.5 32.5 34.5 33 71.0 72 34 35 31
## COMP 32.5 32.5 34.5 33 65.0 31 34 35 31
## TFCP2L1 32.5 32.5 34.5 33 66.0 31 34 35 31
## FOXE1 32.5 32.5 34.5 33 31.5 31 34 35 31
## PLA1A 32.5 0.0 34.5 33 31.5 0 34 35 31
## CLTRN 32.5 32.5 34.5 33 31.5 31 34 35 31
## NIPAL4 32.5 78.0 71.0 33 31.5 31 34 0 0
## SYT1 82.0 0.0 0.0 0 0.0 0 0 0 0
## RASGRP1 32.5 32.5 34.5 33 31.5 31 34 35 31
## KIAA0319 94.0 0.0 0.0 0 0.0 0 0 99 0
## FSTL5 0.0 0.0 72.0 0 0.0 0 87 0 69
## PRELP 0.0 32.5 34.5 33 31.5 31 34 35 31
## LRRC2 32.5 32.5 34.5 0 0.0 31 34 35 31
## SV2B 32.5 32.5 34.5 33 70.0 31 34 35 31
## F11 32.5 68.0 34.5 0 77.0 0 34 0 0
## GLRA1 32.5 32.5 34.5 33 31.5 63 34 0 31
## CTSZ 0.0 0.0 75.0 94 0.0 0 81 0 0
## GCNT4 32.5 32.5 34.5 0 31.5 0 0 35 31
## MPP1 32.5 32.5 34.5 33 31.5 31 34 35 31
## HCN4 32.5 32.5 34.5 0 31.5 31 34 35 31
## LRRTM2 0.0 0.0 0.0 0 0.0 0 0 78 72
## iter56 iter57 iter58 iter59 iter60 iter61 iter62 iter63 iter64
## LSAMP 77 82 84.0 75.0 80.0 87 83.0 81.0 76.0
## REEP1 87 86 90.0 81.0 92.0 94 92.0 89.0 92.0
## CACNG5 85 89 0.0 89.0 87.0 93 85.0 87.0 81.0
## FSTL4 0 78 0.0 71.0 0.0 79 84.0 0.0 82.0
## SLC24A2 71 62 0.0 66.0 79.0 83 72.0 71.0 70.0
## CNTN5 78 71 72.0 32.5 73.0 84 78.0 69.0 0.0
## KCNA1 31 72 88.0 32.5 82.0 73 74.0 0.0 74.0
## PCOLCE2 70 67 65.0 32.5 31.5 74 75.0 33.5 79.0
## NOTUM 86 77 82.0 79.0 0.0 89 32.5 33.5 67.0
## GNAL 80 88 0.0 94.0 90.0 86 88.0 92.0 0.0
## NEFL 72 81 0.0 0.0 83.0 78 0.0 73.0 75.0
## SULF1 81 84 89.0 0.0 86.0 90 0.0 75.0 0.0
## TIAM1 91 91 0.0 92.0 0.0 0 89.0 93.0 0.0
## NXPH3 0 90 0.0 91.0 0.0 0 91.0 95.0 0.0
## GAD1 62 31 66.0 32.5 72.0 68 66.0 33.5 32.5
## TSHR 76 85 0.0 88.0 0.0 0 73.0 0.0 0.0
## DKK3 68 31 75.0 0.0 77.0 72 71.0 33.5 32.5
## ELFN1 31 31 32.5 65.0 31.5 33 32.5 33.5 32.5
## SHISAL1 0 0 0.0 90.0 0.0 0 0.0 96.0 0.0
## ARL4C 31 64 77.0 0.0 31.5 33 32.5 68.0 32.5
## PTCHD4 89 0 87.0 0.0 0.0 92 90.0 74.0 0.0
## SFTPA1 88 0 92.0 0.0 0.0 95 0.0 86.0 89.0
## BARX1 31 31 67.0 32.5 31.5 33 32.5 33.5 32.5
## ARG2 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## CHL1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## GABRA2 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## GRAMD2B 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## OPRD1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## SLC2A2 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## CPXM2 63 31 32.5 32.5 31.5 33 0.0 33.5 32.5
## COMP 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## TFCP2L1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## FOXE1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## PLA1A 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## CLTRN 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## NIPAL4 31 76 0.0 69.0 31.5 0 32.5 33.5 32.5
## SYT1 0 0 0.0 85.0 0.0 0 80.0 80.0 0.0
## RASGRP1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## KIAA0319 0 0 0.0 0.0 0.0 0 94.0 0.0 0.0
## FSTL5 0 0 0.0 0.0 84.0 0 0.0 72.0 86.0
## PRELP 31 31 32.5 32.5 31.5 33 32.5 33.5 0.0
## LRRC2 31 31 32.5 0.0 31.5 33 32.5 33.5 32.5
## SV2B 31 31 32.5 32.5 31.5 33 32.5 0.0 0.0
## F11 31 65 0.0 0.0 31.5 0 32.5 33.5 0.0
## GLRA1 65 31 32.5 0.0 31.5 70 32.5 33.5 32.5
## CTSZ 0 0 81.0 0.0 31.5 76 0.0 33.5 87.0
## GCNT4 0 31 32.5 32.5 31.5 33 32.5 0.0 0.0
## MPP1 31 31 32.5 32.5 31.5 33 32.5 33.5 32.5
## HCN4 31 0 32.5 32.5 0.0 33 32.5 33.5 32.5
## LRRTM2 0 0 0.0 0.0 81.0 0 0.0 0.0 90.0
## iter65 iter66 iter67 iter68 iter69 iter70 iter71 iter72 iter73
## LSAMP 73.0 87 80 78 80.0 77 74 86.0 76
## REEP1 86.0 91 0 80 86.0 81 83 95.0 90
## CACNG5 85.0 90 87 84 87.0 87 82 89.0 86
## FSTL4 76.0 89 74 82 79.0 79 80 85.0 71
## SLC24A2 32.5 83 34 72 66.0 80 69 80.0 74
## CNTN5 78.0 85 34 75 82.0 76 76 75.0 70
## KCNA1 32.5 64 34 68 74.0 72 68 71.0 72
## PCOLCE2 32.5 79 34 32 32.5 34 63 34.5 80
## NOTUM 82.0 65 0 64 77.0 68 64 34.5 82
## GNAL 83.0 88 83 0 88.0 86 85 91.0 0
## NEFL 74.0 0 0 32 67.0 73 75 83.0 31
## SULF1 84.0 0 0 65 0.0 69 0 0.0 88
## TIAM1 91.0 92 91 92 93.0 95 87 96.0 0
## NXPH3 90.0 0 96 86 92.0 93 81 93.0 0
## GAD1 0.0 69 34 32 70.0 34 29 34.5 0
## TSHR 75.0 73 77 71 83.0 83 65 34.5 0
## DKK3 32.5 68 0 32 32.5 34 0 34.5 31
## ELFN1 32.5 32 34 32 32.5 34 29 34.5 31
## SHISAL1 0.0 93 92 90 89.0 88 84 92.0 0
## ARL4C 0.0 0 34 32 0.0 34 29 34.5 64
## PTCHD4 0.0 0 78 0 0.0 82 0 0.0 0
## SFTPA1 0.0 0 0 0 0.0 84 0 0.0 0
## BARX1 32.5 32 34 32 32.5 34 29 34.5 31
## ARG2 32.5 32 34 32 32.5 34 29 34.5 31
## CHL1 32.5 32 34 32 32.5 34 29 34.5 31
## GABRA2 32.5 32 34 32 32.5 34 29 34.5 31
## GRAMD2B 32.5 32 34 32 32.5 34 29 34.5 31
## OPRD1 32.5 32 34 32 32.5 34 29 34.5 31
## SLC2A2 32.5 32 34 32 32.5 34 29 34.5 31
## CPXM2 32.5 0 34 32 32.5 34 29 34.5 31
## COMP 32.5 32 34 32 32.5 34 29 34.5 31
## TFCP2L1 32.5 32 34 32 32.5 34 29 34.5 31
## FOXE1 32.5 32 34 32 32.5 34 29 34.5 31
## PLA1A 32.5 32 34 32 32.5 34 29 34.5 31
## CLTRN 32.5 32 34 32 32.5 34 29 34.5 31
## NIPAL4 32.5 0 34 32 32.5 34 29 34.5 65
## SYT1 79.0 81 71 67 78.0 0 79 34.5 0
## RASGRP1 32.5 32 34 32 32.5 34 29 34.5 31
## KIAA0319 94.0 0 97 93 94.0 97 0 98.0 0
## FSTL5 81.0 0 0 0 0.0 70 0 0.0 89
## PRELP 32.5 0 34 32 32.5 34 0 34.5 31
## LRRC2 32.5 32 34 32 32.5 34 29 34.5 31
## SV2B 32.5 32 34 32 32.5 34 29 34.5 31
## F11 32.5 75 34 32 0.0 34 61 0.0 63
## GLRA1 32.5 32 34 32 32.5 34 0 0.0 31
## CTSZ 0.0 0 0 0 0.0 0 0 0.0 83
## GCNT4 32.5 32 34 32 32.5 0 29 34.5 31
## MPP1 32.5 32 34 32 32.5 34 29 34.5 31
## HCN4 32.5 32 0 32 32.5 34 29 0.0 0
## LRRTM2 87.0 0 0 0 0.0 0 0 0.0 91
## iter74 iter75 iter76 iter77 iter78 iter79 iter80 iter81 iter82
## LSAMP 84.0 84.0 83 90 90.0 93.0 0.0 86 88.0
## REEP1 88.0 85.0 94 95 92.0 96.0 0.0 93 90.0
## CACNG5 87.0 89.0 0 91 93.0 0.0 93.0 89 93.0
## FSTL4 81.0 78.0 82 92 71.0 92.0 0.0 77 89.0
## SLC24A2 75.0 32.5 72 80 69.0 73.0 71.0 33 32.5
## CNTN5 79.0 83.0 33 83 85.0 0.0 0.0 80 83.0
## KCNA1 76.0 32.5 0 89 77.0 0.0 81.0 73 70.0
## PCOLCE2 30.5 70.0 77 76 72.0 80.0 32.5 74 66.0
## NOTUM 0.0 0.0 85 78 87.0 70.0 0.0 72 80.0
## GNAL 86.0 79.0 0 81 91.0 0.0 0.0 92 0.0
## NEFL 85.0 71.0 33 79 88.0 89.0 0.0 70 82.0
## SULF1 0.0 80.0 91 82 80.0 95.0 0.0 78 86.0
## TIAM1 90.0 93.0 0 0 0.0 0.0 0.0 0 0.0
## NXPH3 89.0 0.0 0 0 94.0 0.0 0.0 0 0.0
## GAD1 62.0 32.5 33 33 66.0 0.0 77.0 33 74.0
## TSHR 69.0 0.0 0 0 83.0 0.0 88.0 0 77.0
## DKK3 0.0 32.5 79 73 32.5 75.0 0.0 82 71.0
## ELFN1 30.5 32.5 33 33 32.5 34.5 69.0 33 65.0
## SHISAL1 0.0 0.0 0 0 0.0 0.0 0.0 0 0.0
## ARL4C 65.0 32.5 33 33 0.0 34.5 67.0 33 32.5
## PTCHD4 0.0 87.0 90 0 0.0 94.0 0.0 91 0.0
## SFTPA1 0.0 0.0 0 0 0.0 0.0 0.0 0 94.0
## BARX1 30.5 32.5 33 33 32.5 34.5 0.0 33 32.5
## ARG2 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## CHL1 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## GABRA2 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## GRAMD2B 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## OPRD1 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## SLC2A2 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## CPXM2 30.5 32.5 70 33 32.5 34.5 0.0 33 32.5
## COMP 30.5 32.5 33 33 0.0 34.5 32.5 33 32.5
## TFCP2L1 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## FOXE1 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## PLA1A 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## CLTRN 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## NIPAL4 61.0 0.0 33 33 0.0 34.5 72.0 0 32.5
## SYT1 83.0 0.0 0 0 0.0 0.0 91.0 0 0.0
## RASGRP1 30.5 32.5 33 33 32.5 34.5 0.0 33 32.5
## KIAA0319 0.0 0.0 0 0 0.0 0.0 0.0 0 0.0
## FSTL5 0.0 82.0 0 0 0.0 87.0 0.0 85 84.0
## PRELP 30.5 32.5 33 33 32.5 34.5 32.5 33 32.5
## LRRC2 30.5 32.5 67 33 32.5 34.5 32.5 33 32.5
## SV2B 30.5 0.0 0 33 32.5 0.0 0.0 66 32.5
## F11 63.0 32.5 0 33 0.0 77.0 32.5 33 0.0
## GLRA1 30.5 32.5 33 70 32.5 34.5 32.5 33 32.5
## CTSZ 0.0 74.0 86 86 0.0 85.0 0.0 83 85.0
## GCNT4 30.5 32.5 33 33 32.5 0.0 32.5 33 32.5
## MPP1 30.5 0.0 33 33 32.5 34.5 32.5 33 32.5
## HCN4 30.5 0.0 33 33 32.5 34.5 32.5 33 32.5
## LRRTM2 0.0 81.0 0 0 0.0 0.0 0.0 87 87.0
## iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90 iter91
## LSAMP 82.0 89.0 87 81.0 72 83.0 79 76 80.0
## REEP1 89.0 86.0 92 77.0 81 0.0 92 95 83.0
## CACNG5 95.0 94.0 0 84.0 83 92.0 91 92 92.0
## FSTL4 0.0 82.0 88 76.0 68 79.0 0 0 81.0
## SLC24A2 0.0 74.0 79 80.0 69 80.0 77 77 33.5
## CNTN5 34.5 75.0 0 33.5 70 73.0 78 0 79.0
## KCNA1 81.0 72.0 83 33.5 75 69.0 0 83 33.5
## PCOLCE2 34.5 34.5 76 33.5 32 70.0 65 73 74.0
## NOTUM 0.0 71.0 82 33.5 0 82.0 80 0 33.5
## GNAL 0.0 92.0 0 78.0 85 0.0 0 91 0.0
## NEFL 0.0 79.0 77 69.0 65 84.0 76 0 82.0
## SULF1 74.0 76.0 86 0.0 82 88.0 86 0 76.0
## TIAM1 97.0 95.0 0 94.0 92 94.0 0 0 93.0
## NXPH3 91.0 93.0 0 92.0 90 89.0 0 96 91.0
## GAD1 34.5 34.5 0 33.5 32 32.5 32 71 33.5
## TSHR 0.0 83.0 0 70.0 78 85.0 0 0 73.0
## DKK3 34.5 34.5 73 33.5 0 32.5 64 34 33.5
## ELFN1 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## SHISAL1 98.0 97.0 0 90.0 88 0.0 0 0 94.0
## ARL4C 34.5 34.5 32 33.5 0 0.0 32 34 33.5
## PTCHD4 83.0 88.0 91 0.0 0 0.0 89 0 85.0
## SFTPA1 84.0 96.0 90 88.0 0 90.0 88 0 87.0
## BARX1 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## ARG2 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## CHL1 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## GABRA2 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## GRAMD2B 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## OPRD1 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## SLC2A2 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## CPXM2 34.5 34.5 66 0.0 0 32.5 32 34 33.5
## COMP 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## TFCP2L1 34.5 34.5 32 33.5 0 32.5 32 34 33.5
## FOXE1 34.5 34.5 32 33.5 32 32.5 32 0 33.5
## PLA1A 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## CLTRN 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## NIPAL4 34.5 0.0 32 33.5 32 0.0 32 0 33.5
## SYT1 0.0 90.0 0 73.0 77 0.0 0 0 0.0
## RASGRP1 34.5 34.5 32 33.5 0 32.5 32 0 33.5
## KIAA0319 0.0 98.0 0 96.0 93 0.0 0 0 95.0
## FSTL5 34.5 0.0 89 67.0 0 0.0 83 0 0.0
## PRELP 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## LRRC2 34.5 34.5 0 33.5 32 32.5 32 34 33.5
## SV2B 0.0 34.5 71 33.5 32 32.5 32 0 0.0
## F11 34.5 34.5 67 33.5 32 32.5 0 0 33.5
## GLRA1 0.0 0.0 32 33.5 0 32.5 32 0 33.5
## CTSZ 34.5 0.0 84 0.0 0 0.0 72 0 0.0
## GCNT4 34.5 34.5 32 33.5 32 32.5 32 34 33.5
## MPP1 34.5 0.0 32 33.5 0 32.5 32 0 0.0
## HCN4 34.5 34.5 32 33.5 0 32.5 32 34 33.5
## LRRTM2 70.0 0.0 0 0.0 0 0.0 0 86 0.0
## iter92 iter93 iter94 iter95 iter96 iter97 iter98 iter99 iter100
## LSAMP 89 83 76.0 81.0 82.0 84.0 86.0 84.0 84.0
## REEP1 93 88 81.0 0.0 88.0 0.0 85.0 79.0 90.0
## CACNG5 90 86 90.0 77.0 86.0 85.0 92.0 92.0 92.0
## FSTL4 84 75 68.0 75.0 75.0 0.0 88.0 87.0 86.0
## SLC24A2 80 31 70.0 65.0 70.0 75.0 68.0 75.0 0.0
## CNTN5 88 80 67.0 74.0 0.0 0.0 0.0 78.0 83.0
## KCNA1 85 81 33.5 72.0 76.0 76.0 71.0 33.5 87.0
## PCOLCE2 76 63 33.5 64.0 71.0 69.0 67.0 71.0 72.0
## NOTUM 67 76 0.0 76.0 69.0 0.0 0.0 80.0 75.0
## GNAL 0 89 0.0 0.0 89.0 91.0 87.0 0.0 0.0
## NEFL 86 82 0.0 73.0 31.5 0.0 0.0 0.0 76.0
## SULF1 0 79 0.0 83.0 84.0 0.0 0.0 0.0 78.0
## TIAM1 0 0 95.0 0.0 0.0 92.0 93.0 95.0 0.0
## NXPH3 91 90 91.0 0.0 0.0 86.0 95.0 0.0 0.0
## GAD1 0 71 33.5 30.5 67.0 31.5 80.0 33.5 31.5
## TSHR 0 74 86.0 30.5 0.0 78.0 74.0 82.0 0.0
## DKK3 69 31 0.0 80.0 63.0 0.0 0.0 0.0 31.5
## ELFN1 32 31 33.5 30.5 31.5 64.0 33.5 33.5 31.5
## SHISAL1 0 0 93.0 0.0 0.0 90.0 96.0 91.0 0.0
## ARL4C 32 31 33.5 30.5 0.0 31.5 0.0 33.5 0.0
## PTCHD4 0 85 0.0 0.0 0.0 0.0 0.0 88.0 89.0
## SFTPA1 0 87 0.0 0.0 90.0 0.0 0.0 0.0 0.0
## BARX1 32 31 0.0 30.5 66.0 31.5 33.5 33.5 31.5
## ARG2 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## CHL1 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## GABRA2 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## GRAMD2B 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## OPRD1 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## SLC2A2 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## CPXM2 32 31 33.5 71.0 31.5 31.5 0.0 0.0 31.5
## COMP 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## TFCP2L1 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## FOXE1 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## PLA1A 32 31 0.0 30.5 31.5 31.5 33.5 33.5 31.5
## CLTRN 32 31 0.0 30.5 31.5 31.5 33.5 33.5 31.5
## NIPAL4 32 31 33.5 30.5 0.0 31.5 0.0 70.0 70.0
## SYT1 77 0 89.0 0.0 0.0 87.0 91.0 85.0 0.0
## RASGRP1 0 31 33.5 30.5 31.5 31.5 0.0 33.5 31.5
## KIAA0319 0 91 96.0 0.0 0.0 0.0 0.0 93.0 0.0
## FSTL5 0 78 0.0 0.0 0.0 0.0 0.0 0.0 80.0
## PRELP 0 31 33.5 30.5 31.5 31.5 0.0 33.5 31.5
## LRRC2 32 31 33.5 70.0 31.5 31.5 33.5 33.5 31.5
## SV2B 32 31 0.0 30.5 78.0 31.5 33.5 33.5 65.0
## F11 32 31 0.0 30.5 64.0 31.5 0.0 0.0 68.0
## GLRA1 32 31 0.0 30.5 31.5 0.0 0.0 33.5 31.5
## CTSZ 79 0 0.0 84.0 0.0 0.0 0.0 0.0 77.0
## GCNT4 32 31 33.5 30.5 31.5 31.5 33.5 33.5 31.5
## MPP1 32 31 0.0 30.5 31.5 31.5 0.0 33.5 31.5
## HCN4 32 31 33.5 30.5 31.5 0.0 33.5 33.5 31.5
## LRRTM2 0 0 0.0 0.0 0.0 0.0 0.0 0.0 81.0
## total_rank
## LSAMP 8102.0
## REEP1 8033.0
## CACNG5 7878.0
## FSTL4 6522.0
## SLC24A2 6454.5
## CNTN5 5769.5
## KCNA1 5699.5
## PCOLCE2 5570.0
## NOTUM 5434.0
## GNAL 5309.0
## NEFL 5133.5
## SULF1 5060.0
## TIAM1 4808.0
## NXPH3 4746.0
## GAD1 4502.0
## TSHR 4457.0
## DKK3 4055.5
## ELFN1 3773.0
## SHISAL1 3767.0
## ARL4C 3517.0
## PTCHD4 3479.0
## SFTPA1 3377.0
## BARX1 3261.5
## ARG2 3257.5
## CHL1 3257.5
## GABRA2 3257.5
## GRAMD2B 3257.5
## OPRD1 3257.5
## SLC2A2 3257.5
## CPXM2 3251.0
## COMP 3225.0
## TFCP2L1 3195.0
## FOXE1 3191.0
## PLA1A 3096.0
## CLTRN 3094.5
## NIPAL4 3077.0
## SYT1 3043.0
## RASGRP1 2994.0
## KIAA0319 2941.0
## FSTL5 2921.5
## PRELP 2907.5
## LRRC2 2889.0
## SV2B 2864.5
## F11 2856.0
## GLRA1 2850.5
## CTSZ 2842.5
## GCNT4 2827.0
## MPP1 2797.5
## HCN4 2707.0
## LRRTM2 2705.0write.table(expr_features_comp2_final,file="Comp2_EXPR_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
meth_features_comp1_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),meth_features_comp1)
rownames(meth_features_comp1_final)<-meth_features_comp1_final$GENE
meth_features_comp1_final$GENE<-NULL
meth_features_comp1_final[is.na(meth_features_comp1_final)]<-0
meth_features_comp1_final$total_rank<-rowSums(meth_features_comp1_final)
meth_features_comp1_final<-meth_features_comp1_final[order(-meth_features_comp1_final$total_rank),]
print(head(meth_features_comp1_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10
## cg02988288 100.0 100.0 100.0 100.0 92.0 92.0 100.0 100.0 97.0 99
## cg02966936 93.0 96.0 96.0 94.0 96.0 83.0 97.0 99.0 90.0 93
## cg07175985 89.0 92.0 0.0 93.0 100.0 100.0 93.0 96.0 100.0 92
## cg14527110 98.0 89.0 35.5 97.0 91.0 89.0 98.0 98.0 85.0 35
## cg12220370 96.0 75.0 99.0 91.0 74.0 93.0 94.0 78.0 89.0 98
## cg13566279 99.0 91.0 79.0 96.0 97.0 0.0 99.0 94.0 99.0 87
## cg14490520 76.0 99.0 0.0 86.0 99.0 98.0 86.0 93.0 88.0 74
## cg03770217 82.0 73.0 35.5 98.0 75.0 0.0 75.0 76.0 93.0 0
## cg06184251 35.5 93.0 0.0 35.5 85.0 96.0 83.0 92.0 87.0 0
## cg25934997 85.0 88.0 0.0 0.0 0.0 0.0 96.0 97.0 95.0 0
## cg04577129 71.0 0.0 97.0 83.0 71.0 77.0 87.0 87.0 78.0 95
## cg25979005 73.0 80.0 85.0 77.0 78.0 0.0 71.0 88.0 92.0 84
## cg09467248 35.5 77.0 35.5 99.0 83.0 0.0 85.0 79.0 96.0 0
## cg17826980 72.0 90.0 91.0 35.5 89.0 81.0 35.5 81.0 77.0 0
## cg21165486 95.0 0.0 82.0 90.0 0.0 0.0 77.0 35.5 71.0 96
## cg02736232 35.5 97.0 98.0 35.5 0.0 0.0 84.0 71.0 91.0 0
## cg13336515 86.0 79.0 71.0 35.5 35.5 72.0 35.5 35.5 84.0 82
## cg11515284 97.0 95.0 94.0 35.5 72.0 94.0 35.5 35.5 35.5 35
## cg26767974 92.0 0.0 83.0 72.0 0.0 0.0 81.0 86.0 86.0 77
## cg05627498 94.0 35.5 89.0 89.0 81.0 0.0 90.0 35.5 72.0 72
## cg09449232 84.0 94.0 0.0 92.0 88.0 82.0 79.0 85.0 0.0 35
## cg13176806 79.0 0.0 0.0 88.0 0.0 0.0 88.0 72.0 0.0 83
## cg14534405 75.0 87.0 0.0 84.0 86.0 74.0 35.5 0.0 0.0 0
## cg22364465 91.0 0.0 86.0 35.5 80.0 0.0 95.0 83.0 35.5 88
## cg15275625 0.0 71.0 80.0 95.0 90.0 85.0 35.5 0.0 80.0 0
## cg11743000 90.0 0.0 0.0 85.0 76.0 0.0 89.0 0.0 0.0 94
## cg04255401 0.0 35.5 0.0 87.0 94.0 35.5 92.0 35.5 35.5 75
## cg06749277 0.0 0.0 78.0 79.0 77.0 0.0 78.0 84.0 0.0 73
## cg27044597 35.5 0.0 35.5 35.5 87.0 0.0 35.5 35.5 35.5 0
## cg24196354 0.0 0.0 0.0 76.0 0.0 0.0 91.0 89.0 0.0 0
## cg03220447 0.0 98.0 0.0 0.0 35.5 0.0 0.0 74.0 94.0 0
## cg21533994 35.5 82.0 35.5 35.5 35.5 95.0 35.5 35.5 35.5 35
## cg03726357 35.5 76.0 0.0 35.5 35.5 78.0 35.5 35.5 35.5 0
## cg08248985 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg12451325 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg04934500 80.0 0.0 88.0 80.0 0.0 0.0 73.0 0.0 83.0 0
## cg07270865 74.0 35.5 81.0 0.0 0.0 0.0 0.0 0.0 35.5 85
## cg15630265 35.5 0.0 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg26079959 0.0 81.0 0.0 35.5 35.5 73.0 35.5 35.5 35.5 0
## cg13970113 35.5 0.0 35.5 35.5 35.5 0.0 35.5 0.0 35.5 35
## cg13090941 35.5 0.0 35.5 35.5 35.5 35.5 35.5 90.0 35.5 0
## cg26445440 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg27539060 0.0 0.0 77.0 75.0 95.0 0.0 35.5 0.0 79.0 0
## cg19484548 0.0 0.0 95.0 35.5 98.0 97.0 0.0 0.0 0.0 0
## cg24486540 35.5 35.5 35.5 0.0 0.0 87.0 35.5 35.5 0.0 35
## cg09216797 35.5 0.0 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg00970981 35.5 35.5 35.5 0.0 0.0 0.0 35.5 35.5 0.0 35
## cg24794608 0.0 0.0 92.0 0.0 0.0 0.0 76.0 0.0 81.0 0
## cg12164242 35.5 0.0 35.5 35.5 0.0 0.0 35.5 35.5 35.5 35
## cg03622758 35.5 0.0 35.5 35.5 0.0 0.0 35.5 35.5 35.5 35
## iter11 iter12 iter13 iter14 iter15 iter16 iter17 iter18 iter19
## cg02988288 97.0 100.0 97.0 95.0 97.0 100.0 99 100.0 99.0
## cg02966936 90.0 35.5 96.0 90.0 94.0 98.0 94 98.0 97.0
## cg07175985 99.0 96.0 93.0 100.0 81.0 96.0 91 95.0 94.0
## cg14527110 98.0 35.5 100.0 89.0 100.0 97.0 93 82.0 100.0
## cg12220370 93.0 99.0 0.0 87.0 92.0 35.5 98 92.0 91.0
## cg13566279 91.0 93.0 0.0 98.0 95.0 99.0 96 96.0 93.0
## cg14490520 100.0 0.0 99.0 88.0 0.0 95.0 95 97.0 83.0
## cg03770217 84.0 97.0 83.0 99.0 82.0 83.0 79 35.5 35.5
## cg06184251 96.0 35.5 94.0 35.5 35.5 35.5 97 89.0 87.0
## cg25934997 81.0 88.0 0.0 97.0 73.0 88.0 77 90.0 81.0
## cg04577129 83.0 98.0 0.0 85.0 0.0 75.0 89 78.0 35.5
## cg25979005 89.0 35.5 79.0 96.0 71.0 94.0 80 85.0 79.0
## cg09467248 87.0 35.5 92.0 77.0 99.0 85.0 81 0.0 35.5
## cg17826980 92.0 0.0 98.0 0.0 79.0 86.0 84 91.0 98.0
## cg21165486 72.0 85.0 0.0 35.5 84.0 93.0 72 76.0 96.0
## cg02736232 79.0 0.0 0.0 35.5 35.5 35.5 90 0.0 72.0
## cg13336515 35.5 0.0 74.0 74.0 35.5 35.5 35 72.0 76.0
## cg11515284 80.0 0.0 76.0 0.0 0.0 35.5 0 35.5 90.0
## cg26767974 73.0 95.0 0.0 79.0 72.0 84.0 86 88.0 35.5
## cg05627498 35.5 86.0 0.0 35.5 89.0 92.0 71 83.0 35.5
## cg09449232 75.0 0.0 86.0 81.0 75.0 35.5 0 86.0 95.0
## cg13176806 0.0 84.0 0.0 84.0 86.0 89.0 75 93.0 0.0
## cg14534405 82.0 35.5 0.0 35.5 93.0 35.5 82 0.0 35.5
## cg22364465 0.0 92.0 0.0 71.0 88.0 90.0 87 84.0 77.0
## cg15275625 77.0 0.0 87.0 0.0 98.0 35.5 88 0.0 85.0
## cg11743000 86.0 0.0 0.0 0.0 83.0 76.0 78 94.0 0.0
## cg04255401 35.5 0.0 0.0 35.5 35.5 35.5 35 79.0 35.5
## cg06749277 0.0 87.0 0.0 83.0 0.0 79.0 0 87.0 0.0
## cg27044597 35.5 0.0 80.0 35.5 80.0 35.5 35 35.5 75.0
## cg24196354 35.5 83.0 0.0 72.0 0.0 0.0 83 0.0 0.0
## cg03220447 94.0 35.5 0.0 0.0 35.5 35.5 92 0.0 35.5
## cg21533994 88.0 35.5 90.0 0.0 0.0 35.5 35 35.5 0.0
## cg03726357 74.0 0.0 91.0 35.5 85.0 0.0 35 35.5 71.0
## cg08248985 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg12451325 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg04934500 0.0 91.0 0.0 93.0 0.0 82.0 0 74.0 0.0
## cg07270865 0.0 35.5 0.0 0.0 0.0 77.0 0 0.0 0.0
## cg15630265 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 0.0
## cg26079959 85.0 0.0 88.0 0.0 35.5 0.0 35 0.0 0.0
## cg13970113 0.0 35.5 0.0 35.5 35.5 35.5 35 35.5 0.0
## cg13090941 35.5 35.5 95.0 35.5 35.5 78.0 0 35.5 78.0
## cg26445440 35.5 0.0 0.0 35.5 0.0 35.5 35 35.5 35.5
## cg27539060 0.0 75.0 0.0 92.0 74.0 0.0 0 0.0 0.0
## cg19484548 0.0 0.0 0.0 0.0 78.0 0.0 0 99.0 73.0
## cg24486540 35.5 35.5 35.5 0.0 0.0 35.5 35 35.5 35.5
## cg09216797 35.5 35.5 0.0 0.0 35.5 35.5 35 35.5 35.5
## cg00970981 35.5 35.5 0.0 0.0 0.0 35.5 0 35.5 0.0
## cg24794608 0.0 0.0 0.0 86.0 0.0 0.0 0 77.0 0.0
## cg12164242 35.5 0.0 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg03622758 0.0 35.5 0.0 35.5 35.5 35.5 35 35.5 0.0
## iter20 iter21 iter22 iter23 iter24 iter25 iter26 iter27 iter28
## cg02988288 99 100.0 99.0 99.0 100.0 95 91.0 100.0 98.0
## cg02966936 93 99.0 85.0 95.0 98.0 94 97.0 90.0 85.0
## cg07175985 90 88.0 94.0 97.0 99.0 98 100.0 87.0 75.0
## cg14527110 97 93.0 97.0 93.0 93.0 97 71.0 99.0 82.0
## cg12220370 98 91.0 86.0 76.0 97.0 88 88.0 94.0 73.0
## cg13566279 86 98.0 100.0 100.0 94.0 83 98.0 95.0 83.0
## cg14490520 94 35.5 89.0 96.0 95.0 96 94.0 86.0 92.0
## cg03770217 87 73.0 87.0 92.0 90.0 70 35.5 98.0 0.0
## cg06184251 82 81.0 83.0 94.0 84.0 93 93.0 97.0 99.0
## cg25934997 35 78.0 95.0 86.0 82.0 80 79.0 91.0 91.0
## cg04577129 35 95.0 93.0 91.0 87.0 75 0.0 92.0 0.0
## cg25979005 35 80.0 96.0 87.0 35.5 92 35.5 84.0 0.0
## cg09467248 91 97.0 98.0 89.0 92.0 74 35.5 71.0 93.0
## cg17826980 79 35.5 35.5 35.5 73.0 99 99.0 72.0 100.0
## cg21165486 81 94.0 35.5 35.5 35.5 0 0.0 0.0 0.0
## cg02736232 80 35.5 80.0 80.0 88.0 85 83.0 96.0 0.0
## cg13336515 89 83.0 73.0 35.5 86.0 89 81.0 77.0 0.0
## cg11515284 76 71.0 75.0 88.0 89.0 90 92.0 35.5 0.0
## cg26767974 0 35.5 91.0 35.5 0.0 35 0.0 35.5 79.0
## cg05627498 77 35.5 76.0 75.0 75.0 0 0.0 79.0 89.0
## cg09449232 74 82.0 81.0 90.0 80.0 0 89.0 35.5 71.0
## cg13176806 88 96.0 90.0 71.0 74.0 0 0.0 93.0 0.0
## cg14534405 85 35.5 35.5 98.0 0.0 72 0.0 74.0 35.5
## cg22364465 0 72.0 92.0 35.5 0.0 0 0.0 80.0 86.0
## cg15275625 92 87.0 0.0 0.0 85.0 79 0.0 35.5 96.0
## cg11743000 0 86.0 77.0 72.0 0.0 86 84.0 88.0 94.0
## cg04255401 73 75.0 35.5 74.0 91.0 0 86.0 35.5 35.5
## cg06749277 0 0.0 35.5 0.0 79.0 0 0.0 78.0 0.0
## cg27044597 35 35.5 0.0 0.0 35.5 84 78.0 0.0 35.5
## cg24196354 0 85.0 78.0 0.0 96.0 0 0.0 35.5 0.0
## cg03220447 95 0.0 0.0 35.5 0.0 91 0.0 35.5 97.0
## cg21533994 35 0.0 35.5 35.5 0.0 87 35.5 0.0 87.0
## cg03726357 35 35.5 0.0 78.0 35.5 35 82.0 35.5 0.0
## cg08248985 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg12451325 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg04934500 0 0.0 88.0 85.0 0.0 0 0.0 89.0 0.0
## cg07270865 0 35.5 84.0 0.0 0.0 0 0.0 76.0 35.5
## cg15630265 35 35.5 35.5 35.5 35.5 35 0.0 35.5 35.5
## cg26079959 35 0.0 35.5 35.5 0.0 82 35.5 0.0 90.0
## cg13970113 35 35.5 35.5 35.5 35.5 35 0.0 35.5 35.5
## cg13090941 0 0.0 35.5 0.0 35.5 35 0.0 35.5 35.5
## cg26445440 35 35.5 35.5 0.0 35.5 35 35.5 35.5 35.5
## cg27539060 0 0.0 82.0 0.0 83.0 0 0.0 0.0 0.0
## cg19484548 0 35.5 0.0 0.0 0.0 0 90.0 0.0 95.0
## cg24486540 35 0.0 35.5 0.0 35.5 35 35.5 35.5 0.0
## cg09216797 35 35.5 35.5 35.5 0.0 0 35.5 35.5 0.0
## cg00970981 35 0.0 35.5 35.5 0.0 35 35.5 35.5 35.5
## cg24794608 0 0.0 0.0 0.0 0.0 0 80.0 35.5 0.0
## cg12164242 35 35.5 0.0 35.5 35.5 35 0.0 35.5 35.5
## cg03622758 35 35.5 35.5 35.5 35.5 35 0.0 35.5 0.0
## iter29 iter30 iter31 iter32 iter33 iter34 iter35 iter36 iter37
## cg02988288 100.0 99 99.0 100.0 100.0 100.0 98 100.0 99.0
## cg02966936 94.0 97 72.0 95.0 99.0 99.0 97 97.0 89.0
## cg07175985 95.0 75 90.0 91.0 96.0 89.0 96 98.0 75.0
## cg14527110 98.0 96 98.0 98.0 98.0 88.0 93 95.0 74.0
## cg12220370 74.0 95 87.0 92.0 84.0 98.0 99 73.0 96.0
## cg13566279 82.0 92 96.0 97.0 95.0 93.0 94 99.0 0.0
## cg14490520 96.0 98 97.0 87.0 93.0 74.0 95 88.0 95.0
## cg03770217 85.0 88 77.0 85.0 75.0 78.0 90 84.0 0.0
## cg06184251 84.0 82 79.0 35.5 87.0 35.5 35 85.0 100.0
## cg25934997 97.0 73 0.0 74.0 90.0 96.0 0 94.0 0.0
## cg04577129 79.0 93 88.0 86.0 82.0 97.0 79 0.0 82.0
## cg25979005 89.0 74 0.0 96.0 81.0 35.5 82 0.0 0.0
## cg09467248 90.0 85 84.0 76.0 86.0 0.0 88 91.0 80.0
## cg17826980 93.0 35 35.5 99.0 89.0 35.5 0 78.0 98.0
## cg21165486 83.0 86 93.0 90.0 35.5 95.0 87 79.0 0.0
## cg02736232 92.0 83 35.5 78.0 97.0 92.0 0 35.5 85.0
## cg13336515 35.5 35 0.0 72.0 83.0 35.5 80 82.0 86.0
## cg11515284 71.0 90 94.0 35.5 77.0 80.0 35 90.0 90.0
## cg26767974 99.0 0 0.0 94.0 78.0 0.0 91 0.0 0.0
## cg05627498 77.0 70 0.0 79.0 80.0 83.0 74 35.5 0.0
## cg09449232 87.0 89 86.0 35.5 94.0 81.0 0 83.0 78.0
## cg13176806 0.0 0 0.0 82.0 88.0 90.0 81 92.0 0.0
## cg14534405 35.5 35 85.0 35.5 91.0 0.0 0 93.0 0.0
## cg22364465 75.0 0 0.0 88.0 71.0 84.0 0 35.5 0.0
## cg15275625 35.5 94 81.0 35.5 92.0 0.0 86 0.0 84.0
## cg11743000 0.0 76 89.0 89.0 79.0 35.5 0 89.0 0.0
## cg04255401 0.0 35 75.0 35.5 35.5 86.0 71 35.5 88.0
## cg06749277 78.0 84 0.0 0.0 35.5 87.0 76 0.0 0.0
## cg27044597 81.0 0 73.0 35.5 74.0 0.0 35 75.0 0.0
## cg24196354 80.0 81 35.5 73.0 0.0 79.0 85 0.0 0.0
## cg03220447 91.0 35 35.5 0.0 0.0 0.0 0 74.0 83.0
## cg21533994 35.5 35 35.5 0.0 35.5 35.5 35 0.0 97.0
## cg03726357 35.5 35 78.0 35.5 35.5 0.0 0 86.0 0.0
## cg08248985 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg12451325 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg04934500 76.0 0 0.0 75.0 72.0 91.0 0 76.0 0.0
## cg07270865 72.0 0 0.0 81.0 0.0 35.5 0 35.5 0.0
## cg15630265 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg26079959 35.5 35 35.5 35.5 35.5 0.0 0 0.0 87.0
## cg13970113 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg13090941 35.5 35 71.0 35.5 0.0 35.5 0 0.0 72.0
## cg26445440 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg27539060 0.0 80 0.0 84.0 35.5 35.5 35 0.0 0.0
## cg19484548 0.0 0 0.0 93.0 0.0 0.0 35 0.0 35.5
## cg24486540 0.0 35 76.0 35.5 0.0 35.5 0 0.0 92.0
## cg09216797 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg00970981 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg24794608 35.5 78 0.0 35.5 35.5 94.0 35 72.0 0.0
## cg12164242 35.5 35 0.0 35.5 35.5 35.5 35 35.5 0.0
## cg03622758 0.0 35 0.0 35.5 35.5 35.5 35 35.5 35.5
## iter38 iter39 iter40 iter41 iter42 iter43 iter44 iter45 iter46
## cg02988288 100.0 100.0 100.0 100.0 97 99 97.0 100.0 99
## cg02966936 95.0 99.0 87.0 87.0 86 97 95.0 91.0 92
## cg07175985 82.0 94.0 97.0 90.0 96 90 100.0 93.0 76
## cg14527110 35.5 96.0 96.0 91.0 94 73 99.0 96.0 95
## cg12220370 97.0 97.0 95.0 94.0 92 92 89.0 73.0 98
## cg13566279 83.0 82.0 90.0 92.0 93 88 98.0 97.0 97
## cg14490520 35.5 92.0 85.0 98.0 88 87 87.0 80.0 89
## cg03770217 92.0 95.0 94.0 99.0 76 0 94.0 90.0 96
## cg06184251 35.5 76.0 82.0 84.0 34 0 35.5 76.0 73
## cg25934997 0.0 84.0 71.0 35.5 34 96 84.0 94.0 0
## cg04577129 93.0 91.0 74.0 79.0 90 94 83.0 92.0 91
## cg25979005 0.0 85.0 92.0 72.0 71 91 86.0 95.0 35
## cg09467248 80.0 74.0 89.0 93.0 34 35 71.0 81.0 84
## cg17826980 0.0 98.0 35.5 86.0 0 0 35.5 71.0 0
## cg21165486 84.0 35.5 35.5 35.5 79 89 78.0 98.0 86
## cg02736232 0.0 90.0 35.5 35.5 0 82 0.0 35.5 35
## cg13336515 0.0 87.0 99.0 35.5 70 83 35.5 89.0 0
## cg11515284 35.5 35.5 98.0 0.0 95 98 72.0 35.5 0
## cg26767974 35.5 93.0 88.0 89.0 77 71 76.0 99.0 75
## cg05627498 96.0 0.0 93.0 88.0 0 0 0.0 82.0 85
## cg09449232 35.5 0.0 84.0 82.0 91 35 35.5 35.5 35
## cg13176806 89.0 78.0 35.5 0.0 0 95 90.0 77.0 71
## cg14534405 35.5 88.0 35.5 81.0 34 0 74.0 0.0 94
## cg22364465 35.5 73.0 35.5 35.5 84 35 0.0 87.0 35
## cg15275625 94.0 77.0 35.5 97.0 72 0 0.0 74.0 93
## cg11743000 99.0 0.0 0.0 0.0 81 93 93.0 0.0 81
## cg04255401 35.5 35.5 35.5 0.0 82 84 91.0 35.5 0
## cg06749277 87.0 83.0 0.0 78.0 0 70 80.0 0.0 90
## cg27044597 0.0 86.0 78.0 71.0 0 35 0.0 0.0 0
## cg24196354 0.0 72.0 0.0 83.0 0 0 0.0 85.0 82
## cg03220447 0.0 35.5 0.0 95.0 34 0 0.0 35.5 35
## cg21533994 35.5 35.5 0.0 75.0 34 0 35.5 0.0 35
## cg03726357 0.0 89.0 35.5 35.5 34 0 35.5 35.5 0
## cg08248985 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg12451325 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg04934500 71.0 0.0 0.0 35.5 0 0 79.0 0.0 0
## cg07270865 0.0 35.5 35.5 35.5 0 86 0.0 84.0 0
## cg15630265 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg26079959 35.5 35.5 0.0 85.0 0 0 35.5 0.0 35
## cg13970113 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg13090941 0.0 35.5 35.5 0.0 34 0 0.0 0.0 0
## cg26445440 0.0 35.5 35.5 35.5 34 35 0.0 35.5 35
## cg27539060 0.0 35.5 0.0 80.0 0 0 0.0 75.0 35
## cg19484548 91.0 81.0 79.0 0.0 0 35 0.0 0.0 0
## cg24486540 35.5 0.0 35.5 0.0 34 35 35.5 35.5 0
## cg09216797 35.5 35.5 35.5 0.0 34 35 35.5 35.5 35
## cg00970981 35.5 35.5 0.0 35.5 34 35 35.5 35.5 35
## cg24794608 35.5 0.0 0.0 74.0 0 0 0.0 35.5 35
## cg12164242 0.0 35.5 35.5 0.0 34 35 0.0 35.5 35
## cg03622758 35.5 35.5 35.5 0.0 34 35 35.5 35.5 35
## iter47 iter48 iter49 iter50 iter51 iter52 iter53 iter54 iter55
## cg02988288 99 100.0 100.0 96.0 100.0 99.0 100.0 100.0 100.0
## cg02966936 95 81.0 98.0 97.0 79.0 96.0 96.0 94.0 96.0
## cg07175985 92 96.0 71.0 92.0 77.0 95.0 93.0 82.0 98.0
## cg14527110 97 88.0 82.0 88.0 98.0 98.0 98.0 96.0 97.0
## cg12220370 90 95.0 97.0 35.5 78.0 91.0 88.0 97.0 78.0
## cg13566279 98 99.0 99.0 35.5 94.0 35.5 92.0 98.0 86.0
## cg14490520 82 35.5 85.0 99.0 90.0 88.0 97.0 81.0 93.0
## cg03770217 96 83.0 35.5 78.0 0.0 78.0 90.0 71.0 82.0
## cg06184251 35 0.0 35.5 98.0 99.0 90.0 99.0 91.0 99.0
## cg25934997 78 85.0 91.0 77.0 92.0 83.0 91.0 76.0 95.0
## cg04577129 35 90.0 84.0 0.0 84.0 73.0 0.0 85.0 0.0
## cg25979005 35 94.0 79.0 83.0 35.5 35.5 73.0 0.0 80.0
## cg09467248 91 0.0 72.0 0.0 95.0 0.0 35.5 83.0 89.0
## cg17826980 35 0.0 74.0 100.0 89.0 100.0 94.0 77.0 91.0
## cg21165486 72 78.0 90.0 0.0 35.5 0.0 35.5 93.0 79.0
## cg02736232 75 35.5 95.0 84.0 82.0 97.0 89.0 0.0 72.0
## cg13336515 35 77.0 0.0 35.5 71.0 82.0 72.0 35.5 90.0
## cg11515284 84 74.0 0.0 35.5 0.0 93.0 35.5 0.0 35.5
## cg26767974 0 86.0 78.0 75.0 75.0 35.5 80.0 35.5 0.0
## cg05627498 94 87.0 81.0 72.0 83.0 0.0 71.0 90.0 0.0
## cg09449232 35 0.0 0.0 0.0 35.5 35.5 35.5 89.0 85.0
## cg13176806 89 84.0 88.0 0.0 76.0 0.0 84.0 84.0 84.0
## cg14534405 80 35.5 0.0 0.0 81.0 35.5 95.0 95.0 92.0
## cg22364465 86 93.0 96.0 0.0 93.0 0.0 86.0 87.0 71.0
## cg15275625 77 35.5 0.0 0.0 85.0 0.0 0.0 80.0 0.0
## cg11743000 0 91.0 0.0 0.0 96.0 35.5 87.0 99.0 0.0
## cg04255401 0 0.0 0.0 35.5 0.0 74.0 78.0 35.5 35.5
## cg06749277 85 79.0 89.0 0.0 0.0 0.0 79.0 88.0 77.0
## cg27044597 0 0.0 0.0 76.0 0.0 35.5 81.0 0.0 83.0
## cg24196354 70 0.0 80.0 0.0 0.0 0.0 35.5 0.0 0.0
## cg03220447 73 0.0 0.0 93.0 97.0 35.5 35.5 35.5 81.0
## cg21533994 35 0.0 35.5 94.0 91.0 35.5 74.0 35.5 35.5
## cg03726357 35 0.0 0.0 35.5 0.0 87.0 35.5 0.0 76.0
## cg08248985 35 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5
## cg12451325 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg04934500 88 89.0 92.0 0.0 0.0 0.0 0.0 0.0 0.0
## cg07270865 79 80.0 75.0 0.0 74.0 0.0 35.5 35.5 0.0
## cg15630265 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg26079959 35 0.0 0.0 90.0 87.0 0.0 35.5 74.0 88.0
## cg13970113 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg13090941 35 0.0 35.5 73.0 35.5 86.0 82.0 35.5 35.5
## cg26445440 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg27539060 87 35.5 77.0 0.0 0.0 0.0 0.0 0.0 0.0
## cg19484548 0 0.0 35.5 87.0 0.0 81.0 76.0 0.0 0.0
## cg24486540 0 35.5 35.5 35.5 35.5 84.0 35.5 35.5 35.5
## cg09216797 0 35.5 35.5 35.5 35.5 0.0 35.5 35.5 0.0
## cg00970981 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg24794608 0 0.0 93.0 74.0 0.0 71.0 0.0 0.0 0.0
## cg12164242 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg03622758 35 35.5 35.5 35.5 0.0 0.0 35.5 35.5 0.0
## iter56 iter57 iter58 iter59 iter60 iter61 iter62 iter63 iter64
## cg02988288 99.0 100.0 100.0 99 100.0 100.0 96 99 93.0
## cg02966936 82.0 90.0 98.0 92 97.0 86.0 97 91 90.0
## cg07175985 98.0 98.0 88.0 91 99.0 84.0 94 88 100.0
## cg14527110 91.0 97.0 99.0 93 92.0 99.0 98 94 96.0
## cg12220370 89.0 93.0 72.0 98 93.0 72.0 89 97 79.0
## cg13566279 95.0 95.0 89.0 87 87.0 90.0 95 90 91.0
## cg14490520 100.0 94.0 87.0 74 81.0 94.0 93 96 99.0
## cg03770217 86.0 96.0 92.0 76 98.0 73.0 75 80 86.0
## cg06184251 94.0 88.0 82.0 0 94.0 95.0 85 93 98.0
## cg25934997 0.0 77.0 95.0 0 96.0 85.0 84 85 0.0
## cg04577129 0.0 87.0 84.0 89 0.0 81.0 87 81 0.0
## cg25979005 74.0 83.0 35.5 0 35.5 79.0 92 0 74.0
## cg09467248 75.0 72.0 35.5 0 85.0 93.0 35 84 88.0
## cg17826980 88.0 35.5 35.5 0 73.0 96.0 99 0 94.0
## cg21165486 87.0 35.5 81.0 72 35.5 35.5 35 75 0.0
## cg02736232 76.0 78.0 83.0 35 0.0 77.0 90 35 84.0
## cg13336515 83.0 91.0 0.0 35 75.0 89.0 76 0 92.0
## cg11515284 72.0 99.0 93.0 78 82.0 78.0 35 95 85.0
## cg26767974 35.5 0.0 35.5 35 35.5 88.0 88 0 0.0
## cg05627498 71.0 76.0 79.0 80 84.0 0.0 81 74 0.0
## cg09449232 0.0 92.0 35.5 85 86.0 83.0 35 35 75.0
## cg13176806 0.0 0.0 90.0 88 89.0 0.0 86 83 0.0
## cg14534405 97.0 89.0 0.0 95 35.5 80.0 0 0 76.0
## cg22364465 0.0 82.0 75.0 90 35.5 0.0 91 35 0.0
## cg15275625 85.0 35.5 85.0 86 91.0 91.0 0 87 87.0
## cg11743000 0.0 0.0 80.0 96 88.0 0.0 78 98 0.0
## cg04255401 81.0 71.0 35.5 35 35.5 0.0 0 35 35.5
## cg06749277 0.0 0.0 0.0 83 35.5 0.0 79 82 0.0
## cg27044597 80.0 35.5 71.0 0 95.0 71.0 70 35 78.0
## cg24196354 0.0 0.0 35.5 35 90.0 76.0 0 0 0.0
## cg03220447 96.0 74.0 74.0 35 0.0 98.0 35 0 95.0
## cg21533994 90.0 35.5 0.0 0 77.0 82.0 0 35 35.5
## cg03726357 79.0 84.0 35.5 35 35.5 35.5 35 35 82.0
## cg08248985 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg12451325 35.5 35.5 35.5 35 35.5 0.0 35 35 0.0
## cg04934500 0.0 0.0 0.0 0 35.5 0.0 0 0 0.0
## cg07270865 35.5 35.5 0.0 0 35.5 0.0 74 35 0.0
## cg15630265 0.0 35.5 35.5 35 35.5 0.0 35 35 0.0
## cg26079959 84.0 0.0 0.0 0 76.0 75.0 35 35 81.0
## cg13970113 0.0 0.0 35.5 35 35.5 0.0 35 35 0.0
## cg13090941 0.0 0.0 35.5 0 78.0 35.5 73 35 0.0
## cg26445440 0.0 35.5 35.5 35 35.5 0.0 35 35 0.0
## cg27539060 0.0 0.0 0.0 0 0.0 0.0 80 0 0.0
## cg19484548 0.0 0.0 91.0 79 80.0 0.0 77 35 0.0
## cg24486540 35.5 79.0 0.0 35 35.5 35.5 0 73 35.5
## cg09216797 0.0 0.0 35.5 35 35.5 0.0 35 35 35.5
## cg00970981 0.0 0.0 35.5 35 35.5 0.0 35 35 0.0
## cg24794608 0.0 0.0 0.0 35 35.5 0.0 82 0 0.0
## cg12164242 0.0 35.5 35.5 35 0.0 0.0 35 35 0.0
## cg03622758 0.0 0.0 35.5 35 0.0 35.5 35 35 0.0
## iter65 iter66 iter67 iter68 iter69 iter70 iter71 iter72 iter73
## cg02988288 98 99 98 95 100.0 99 98.0 99 99.0
## cg02966936 89 95 93 88 96.0 94 92.0 94 89.0
## cg07175985 96 94 89 98 95.0 97 100.0 84 96.0
## cg14527110 91 87 83 96 85.0 95 99.0 92 95.0
## cg12220370 88 97 87 89 98.0 98 97.0 96 85.0
## cg13566279 99 92 95 99 99.0 96 90.0 95 0.0
## cg14490520 94 96 96 97 94.0 93 95.0 35 100.0
## cg03770217 90 91 35 92 88.0 91 91.0 74 0.0
## cg06184251 95 83 82 35 35.5 74 87.0 35 97.0
## cg25934997 97 88 35 87 72.0 85 78.0 70 78.0
## cg04577129 92 84 92 85 90.0 90 88.0 91 0.0
## cg25979005 74 89 91 83 93.0 86 81.0 35 0.0
## cg09467248 76 75 84 94 83.0 83 35.5 82 0.0
## cg17826980 35 35 94 35 0.0 82 84.0 35 88.0
## cg21165486 35 93 90 71 35.5 72 0.0 89 0.0
## cg02736232 35 0 35 78 78.0 89 35.5 35 87.0
## cg13336515 73 35 85 73 35.5 35 93.0 85 35.5
## cg11515284 72 0 70 93 86.0 78 96.0 35 83.0
## cg26767974 35 86 99 35 0.0 81 0.0 88 35.5
## cg05627498 77 98 35 0 35.5 0 79.0 93 0.0
## cg09449232 93 35 79 35 35.5 35 89.0 98 93.0
## cg13176806 82 85 0 0 92.0 73 0.0 0 0.0
## cg14534405 87 0 0 91 87.0 75 86.0 72 92.0
## cg22364465 84 81 0 82 71.0 84 71.0 90 0.0
## cg15275625 0 70 0 0 82.0 0 0.0 73 73.0
## cg11743000 70 0 80 0 89.0 80 0.0 97 0.0
## cg04255401 35 0 88 74 80.0 88 77.0 78 0.0
## cg06749277 78 90 0 0 79.0 0 0.0 77 0.0
## cg27044597 35 82 35 0 35.5 35 85.0 0 0.0
## cg24196354 85 79 71 0 77.0 92 80.0 0 0.0
## cg03220447 35 0 0 35 0.0 35 35.5 35 98.0
## cg21533994 35 35 35 0 0.0 0 35.5 0 86.0
## cg03726357 0 0 0 35 0.0 0 82.0 35 91.0
## cg08248985 35 35 35 35 35.5 35 35.5 35 0.0
## cg12451325 35 35 35 35 35.5 35 35.5 35 0.0
## cg04934500 83 80 0 84 75.0 0 0.0 0 0.0
## cg07270865 35 73 86 35 35.5 0 0.0 35 0.0
## cg15630265 35 35 35 35 35.5 35 35.5 35 0.0
## cg26079959 0 35 0 35 0.0 0 75.0 0 74.0
## cg13970113 35 35 35 35 35.5 35 35.5 35 0.0
## cg13090941 35 35 0 35 0.0 0 35.5 0 0.0
## cg26445440 35 35 35 0 35.5 35 35.5 35 0.0
## cg27539060 0 35 76 86 0.0 0 0.0 0 0.0
## cg19484548 35 0 97 0 84.0 0 0.0 79 0.0
## cg24486540 35 35 35 35 0.0 35 35.5 35 35.5
## cg09216797 35 35 35 35 35.5 35 0.0 35 0.0
## cg00970981 35 35 35 35 35.5 35 35.5 35 35.5
## cg24794608 79 0 74 0 35.5 87 0.0 0 0.0
## cg12164242 35 35 0 35 35.5 35 35.5 0 0.0
## cg03622758 35 35 35 35 35.5 35 35.5 35 0.0
## iter74 iter75 iter76 iter77 iter78 iter79 iter80 iter81 iter82
## cg02988288 98 97.0 99.0 100.0 100.0 100.0 100.0 100.0 97.0
## cg02966936 89 94.0 100.0 98.0 97.0 99.0 96.0 95.0 99.0
## cg07175985 99 100.0 97.0 91.0 85.0 87.0 92.0 97.0 100.0
## cg14527110 91 78.0 94.0 87.0 92.0 93.0 95.0 85.0 83.0
## cg12220370 92 90.0 79.0 96.0 99.0 96.0 94.0 98.0 91.0
## cg13566279 97 95.0 95.0 94.0 93.0 75.0 97.0 35.5 96.0
## cg14490520 96 89.0 90.0 99.0 86.0 98.0 81.0 35.5 95.0
## cg03770217 94 99.0 35.5 0.0 94.0 35.5 91.0 81.0 98.0
## cg06184251 83 35.5 89.0 97.0 95.0 92.0 35.5 35.5 35.5
## cg25934997 88 80.0 85.0 84.0 91.0 0.0 35.5 96.0 87.0
## cg04577129 85 98.0 0.0 85.0 87.0 88.0 90.0 76.0 94.0
## cg25979005 93 96.0 35.5 0.0 78.0 0.0 71.0 87.0 93.0
## cg09467248 81 84.0 74.0 0.0 73.0 0.0 82.0 0.0 80.0
## cg17826980 35 35.5 98.0 86.0 35.5 89.0 0.0 35.5 35.5
## cg21165486 35 91.0 96.0 0.0 35.5 84.0 35.5 93.0 71.0
## cg02736232 35 35.5 92.0 88.0 96.0 95.0 0.0 71.0 77.0
## cg13336515 76 0.0 78.0 0.0 35.5 0.0 72.0 84.0 35.5
## cg11515284 0 0.0 35.5 92.0 35.5 94.0 35.5 0.0 35.5
## cg26767974 95 85.0 84.0 0.0 89.0 0.0 89.0 92.0 89.0
## cg05627498 86 77.0 88.0 0.0 35.5 82.0 0.0 94.0 0.0
## cg09449232 35 0.0 35.5 76.0 35.5 0.0 80.0 0.0 35.5
## cg13176806 82 86.0 91.0 82.0 80.0 0.0 84.0 99.0 78.0
## cg14534405 87 35.5 0.0 90.0 83.0 0.0 85.0 0.0 35.5
## cg22364465 0 0.0 35.5 0.0 0.0 77.0 35.5 73.0 0.0
## cg15275625 0 0.0 86.0 0.0 35.5 79.0 93.0 0.0 0.0
## cg11743000 75 79.0 0.0 77.0 0.0 0.0 98.0 0.0 75.0
## cg04255401 0 0.0 82.0 35.5 35.5 72.0 83.0 35.5 35.5
## cg06749277 80 81.0 80.0 35.5 0.0 0.0 0.0 90.0 0.0
## cg27044597 70 0.0 81.0 83.0 35.5 85.0 0.0 0.0 79.0
## cg24196354 0 0.0 83.0 78.0 84.0 0.0 35.5 0.0 76.0
## cg03220447 35 0.0 35.5 0.0 98.0 0.0 35.5 0.0 35.5
## cg21533994 35 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5
## cg03726357 35 0.0 35.5 35.5 76.0 0.0 35.5 0.0 35.5
## cg08248985 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg12451325 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg04934500 78 92.0 0.0 0.0 82.0 0.0 0.0 35.5 81.0
## cg07270865 35 35.5 35.5 0.0 0.0 0.0 73.0 89.0 0.0
## cg15630265 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg26079959 35 35.5 71.0 35.5 77.0 0.0 0.0 0.0 35.5
## cg13970113 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg13090941 0 35.5 35.5 0.0 35.5 35.5 0.0 0.0 35.5
## cg26445440 35 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5
## cg27539060 84 87.0 35.5 0.0 0.0 0.0 0.0 0.0 88.0
## cg19484548 0 35.5 93.0 0.0 0.0 97.0 79.0 35.5 0.0
## cg24486540 0 0.0 0.0 35.5 0.0 35.5 0.0 35.5 0.0
## cg09216797 35 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5
## cg00970981 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg24794608 0 76.0 72.0 75.0 90.0 0.0 0.0 86.0 82.0
## cg12164242 35 0.0 0.0 35.5 35.5 35.5 35.5 35.5 35.5
## cg03622758 35 35.5 0.0 0.0 35.5 35.5 35.5 35.5 35.5
## iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90 iter91
## cg02988288 98 100.0 100.0 98.0 95.0 100.0 100.0 100.0 98.0
## cg02966936 94 95.0 98.0 100.0 0.0 96.0 99.0 91.0 92.0
## cg07175985 99 97.0 75.0 96.0 94.0 98.0 95.0 83.0 97.0
## cg14527110 91 84.0 35.5 95.0 99.0 94.0 92.0 98.0 76.0
## cg12220370 96 93.0 76.0 94.0 92.0 86.0 90.0 90.0 100.0
## cg13566279 95 98.0 95.0 97.0 84.0 95.0 93.0 97.0 99.0
## cg14490520 92 94.0 85.0 99.0 90.0 92.0 98.0 86.0 82.0
## cg03770217 93 83.0 74.0 86.0 73.0 99.0 91.0 0.0 96.0
## cg06184251 35 35.5 96.0 79.0 93.0 93.0 97.0 96.0 35.5
## cg25934997 83 85.0 99.0 93.0 0.0 97.0 94.0 94.0 75.0
## cg04577129 85 99.0 0.0 83.0 0.0 0.0 82.0 0.0 93.0
## cg25979005 87 96.0 84.0 92.0 83.0 84.0 35.5 0.0 79.0
## cg09467248 90 82.0 35.5 77.0 85.0 35.5 75.0 81.0 95.0
## cg17826980 35 0.0 92.0 90.0 35.5 35.5 80.0 88.0 0.0
## cg21165486 97 88.0 35.5 88.0 81.0 0.0 77.0 80.0 91.0
## cg02736232 0 90.0 97.0 74.0 0.0 35.5 35.5 0.0 35.5
## cg13336515 76 35.5 35.5 78.0 100.0 35.5 35.5 73.0 0.0
## cg11515284 35 86.0 0.0 85.0 97.0 73.0 87.0 95.0 0.0
## cg26767974 86 35.5 91.0 71.0 72.0 76.0 0.0 35.5 94.0
## cg05627498 74 0.0 93.0 0.0 0.0 35.5 76.0 35.5 89.0
## cg09449232 82 35.5 0.0 35.5 82.0 82.0 85.0 99.0 0.0
## cg13176806 0 87.0 90.0 76.0 0.0 90.0 0.0 0.0 87.0
## cg14534405 73 75.0 0.0 35.5 80.0 77.0 73.0 89.0 80.0
## cg22364465 0 73.0 72.0 89.0 0.0 35.5 84.0 74.0 35.5
## cg15275625 75 35.5 79.0 0.0 0.0 0.0 0.0 0.0 86.0
## cg11743000 79 78.0 0.0 81.0 87.0 0.0 0.0 0.0 0.0
## cg04255401 35 92.0 0.0 35.5 35.5 72.0 35.5 76.0 83.0
## cg06749277 81 35.5 80.0 84.0 0.0 79.0 0.0 0.0 0.0
## cg27044597 72 0.0 35.5 73.0 0.0 35.5 81.0 35.5 35.5
## cg24196354 77 81.0 0.0 72.0 0.0 91.0 96.0 0.0 35.5
## cg03220447 35 0.0 89.0 35.5 0.0 35.5 35.5 35.5 85.0
## cg21533994 35 0.0 35.5 35.5 74.0 35.5 35.5 35.5 0.0
## cg03726357 35 0.0 0.0 35.5 76.0 35.5 35.5 72.0 35.5
## cg08248985 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg12451325 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg04934500 0 79.0 87.0 0.0 0.0 81.0 0.0 0.0 88.0
## cg07270865 70 74.0 88.0 91.0 91.0 0.0 0.0 0.0 0.0
## cg15630265 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg26079959 0 0.0 35.5 0.0 0.0 0.0 35.5 35.5 0.0
## cg13970113 35 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5
## cg13090941 35 0.0 0.0 35.5 35.5 0.0 79.0 92.0 0.0
## cg26445440 35 35.5 0.0 35.5 35.5 0.0 35.5 35.5 35.5
## cg27539060 89 89.0 0.0 35.5 0.0 71.0 71.0 0.0 0.0
## cg19484548 0 0.0 0.0 35.5 0.0 35.5 0.0 0.0 0.0
## cg24486540 35 35.5 0.0 35.5 98.0 35.5 35.5 35.5 0.0
## cg09216797 35 35.5 0.0 35.5 35.5 35.5 0.0 35.5 35.5
## cg00970981 35 35.5 35.5 35.5 35.5 0.0 0.0 35.5 35.5
## cg24794608 0 35.5 78.0 0.0 0.0 88.0 0.0 0.0 35.5
## cg12164242 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg03622758 35 35.5 35.5 35.5 0.0 0.0 0.0 35.5 35.5
## iter92 iter93 iter94 iter95 iter96 iter97 iter98 iter99 iter100
## cg02988288 100.0 100.0 100.0 99.0 100.0 99.0 99.0 99.0 96
## cg02966936 97.0 81.0 95.0 98.0 99.0 95.0 90.0 97.0 97
## cg07175985 98.0 90.0 93.0 100.0 83.0 100.0 96.0 98.0 98
## cg14527110 99.0 92.0 98.0 96.0 85.0 98.0 80.0 90.0 74
## cg12220370 88.0 99.0 92.0 78.0 84.0 93.0 97.0 81.0 88
## cg13566279 94.0 83.0 94.0 75.0 92.0 96.0 100.0 100.0 92
## cg14490520 83.0 95.0 96.0 88.0 71.0 88.0 87.0 96.0 95
## cg03770217 95.0 96.0 83.0 83.0 82.0 86.0 77.0 35.5 90
## cg06184251 71.0 79.0 89.0 95.0 75.0 81.0 35.5 75.0 91
## cg25934997 93.0 71.0 78.0 93.0 98.0 0.0 86.0 92.0 99
## cg04577129 87.0 82.0 91.0 0.0 0.0 85.0 93.0 83.0 73
## cg25979005 96.0 91.0 76.0 87.0 94.0 82.0 79.0 82.0 82
## cg09467248 91.0 73.0 85.0 0.0 74.0 92.0 81.0 85.0 35
## cg17826980 75.0 74.0 87.0 72.0 35.5 84.0 35.5 94.0 72
## cg21165486 78.0 86.0 0.0 0.0 81.0 35.5 98.0 0.0 78
## cg02736232 76.0 72.0 35.5 86.0 80.0 75.0 35.5 80.0 93
## cg13336515 72.0 85.0 0.0 90.0 35.5 72.0 35.5 35.5 87
## cg11515284 0.0 35.5 0.0 89.0 0.0 35.5 35.5 76.0 85
## cg26767974 84.0 88.0 73.0 0.0 91.0 89.0 78.0 0.0 81
## cg05627498 74.0 84.0 0.0 0.0 90.0 35.5 35.5 89.0 84
## cg09449232 0.0 0.0 99.0 85.0 35.5 91.0 35.5 35.5 0
## cg13176806 80.0 0.0 0.0 91.0 96.0 0.0 71.0 91.0 75
## cg14534405 0.0 97.0 80.0 35.5 0.0 87.0 0.0 0.0 35
## cg22364465 0.0 93.0 0.0 0.0 72.0 74.0 0.0 84.0 0
## cg15275625 0.0 94.0 88.0 0.0 95.0 83.0 35.5 0.0 0
## cg11743000 0.0 0.0 97.0 0.0 78.0 77.0 35.5 35.5 0
## cg04255401 0.0 35.5 90.0 35.5 0.0 94.0 35.5 35.5 0
## cg06749277 81.0 0.0 0.0 0.0 88.0 0.0 0.0 79.0 79
## cg27044597 35.5 35.5 0.0 35.5 35.5 0.0 83.0 35.5 80
## cg24196354 85.0 0.0 86.0 0.0 0.0 78.0 85.0 35.5 0
## cg03220447 0.0 98.0 0.0 77.0 89.0 0.0 0.0 0.0 35
## cg21533994 35.5 76.0 35.5 35.5 35.5 35.5 35.5 0.0 35
## cg03726357 35.5 0.0 35.5 94.0 0.0 35.5 0.0 35.5 0
## cg08248985 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg12451325 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg04934500 0.0 0.0 0.0 0.0 79.0 0.0 35.5 87.0 83
## cg07270865 77.0 80.0 0.0 0.0 35.5 0.0 88.0 35.5 35
## cg15630265 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35
## cg26079959 35.5 35.5 35.5 35.5 35.5 35.5 0.0 0.0 35
## cg13970113 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35
## cg13090941 35.5 0.0 35.5 35.5 0.0 71.0 35.5 35.5 35
## cg26445440 35.5 35.5 35.5 0.0 35.5 35.5 35.5 0.0 35
## cg27539060 92.0 0.0 74.0 0.0 0.0 97.0 95.0 0.0 35
## cg19484548 0.0 0.0 0.0 0.0 0.0 90.0 0.0 72.0 0
## cg24486540 0.0 35.5 0.0 35.5 0.0 0.0 35.5 35.5 0
## cg09216797 35.5 0.0 35.5 0.0 35.5 35.5 35.5 35.5 0
## cg00970981 0.0 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35
## cg24794608 35.5 0.0 79.0 0.0 0.0 0.0 0.0 0.0 89
## cg12164242 35.5 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35
## cg03622758 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35
## total_rank
## cg02988288 9869.0
## cg02966936 9199.5
## cg07175985 9174.0
## cg14527110 8944.0
## cg12220370 8809.0
## cg13566279 8784.5
## cg14490520 8553.0
## cg03770217 7394.0
## cg06184251 7085.5
## cg25934997 6932.0
## cg04577129 6741.5
## cg25979005 6649.0
## cg09467248 6635.0
## cg17826980 6001.5
## cg21165486 5770.5
## cg02736232 5648.5
## cg13336515 5626.5
## cg11515284 5624.5
## cg26767974 5576.5
## cg05627498 5532.5
## cg09449232 5456.5
## cg13176806 5374.5
## cg14534405 5002.5
## cg22364465 4913.0
## cg15275625 4719.5
## cg11743000 4659.0
## cg04255401 4424.0
## cg06749277 3999.5
## cg27044597 3919.5
## cg24196354 3664.0
## cg03220447 3657.5
## cg21533994 3566.5
## cg03726357 3483.5
## cg08248985 3396.0
## cg12451325 3289.5
## cg04934500 3196.0
## cg07270865 3082.0
## cg15630265 3076.5
## cg26079959 3037.5
## cg13970113 2934.5
## cg13090941 2887.0
## cg26445440 2828.5
## cg27539060 2782.5
## cg19484548 2755.0
## cg24486540 2746.0
## cg09216797 2723.0
## cg00970981 2686.5
## cg24794608 2680.5
## cg12164242 2651.5
## cg03622758 2650.5write.table(meth_features_comp1_final,file="Comp1_METH_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
meth_features_comp2_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),meth_features_comp2)
rownames(meth_features_comp2_final)<-meth_features_comp2_final$GENE
meth_features_comp2_final$GENE<-NULL
meth_features_comp2_final[is.na(meth_features_comp2_final)]<-0
meth_features_comp2_final$total_rank<-rowSums(meth_features_comp2_final)
meth_features_comp2_final<-meth_features_comp2_final[order(-meth_features_comp2_final$total_rank),]
print(head(meth_features_comp2_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10
## cg12451325 98.0 82.0 86.0 94.0 35.5 0.0 96.0 92.0 79.0 94
## cg08248985 94.0 35.5 35.5 90.0 76.0 0.0 84.0 87.0 78.0 92
## cg26445440 87.0 35.5 95.0 97.0 95.0 0.0 85.0 74.0 77.0 87
## cg12164242 95.0 0.0 98.0 98.0 0.0 0.0 88.0 84.0 81.0 97
## cg15630265 89.0 0.0 35.5 87.0 35.5 0.0 87.0 73.0 72.0 82
## cg09216797 96.0 0.0 78.0 78.0 97.0 0.0 90.0 83.0 85.0 73
## cg13544025 93.0 0.0 97.0 100.0 0.0 0.0 97.0 89.0 88.0 93
## cg27179424 97.0 0.0 0.0 99.0 0.0 0.0 100.0 97.0 89.0 95
## cg22152677 0.0 86.0 77.0 0.0 79.0 0.0 99.0 91.0 87.0 0
## cg12084792 0.0 0.0 0.0 96.0 77.0 0.0 0.0 75.0 0.0 0
## cg03622758 78.0 0.0 81.0 85.0 0.0 0.0 82.0 35.5 35.5 79
## cg14228710 0.0 35.5 85.0 0.0 72.0 0.0 0.0 79.0 35.5 0
## cg13559778 83.0 0.0 90.0 86.0 0.0 0.0 89.0 35.5 0.0 75
## cg07523470 75.0 0.0 0.0 92.0 0.0 0.0 92.0 35.5 0.0 78
## cg16901379 99.0 0.0 0.0 0.0 0.0 0.0 0.0 95.0 82.0 96
## cg08571304 81.0 0.0 76.0 84.0 0.0 0.0 75.0 35.5 0.0 84
## cg04684637 82.0 0.0 0.0 91.0 0.0 0.0 83.0 35.5 86.0 72
## cg12546646 0.0 0.0 0.0 76.0 0.0 0.0 71.0 35.5 0.0 0
## cg20836795 91.0 0.0 35.5 82.0 35.5 0.0 35.5 35.5 0.0 90
## cg20189782 71.0 0.0 0.0 77.0 0.0 0.0 93.0 35.5 0.0 71
## cg27051815 0.0 0.0 0.0 0.0 93.0 0.0 0.0 0.0 100.0 0
## cg00970981 85.0 35.5 35.5 0.0 0.0 0.0 78.0 35.5 0.0 80
## cg12747056 100.0 0.0 0.0 0.0 0.0 0.0 0.0 93.0 99.0 0
## cg02988288 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg14527110 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg02966936 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg07175985 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg12220370 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg14490520 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg13566279 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg06184251 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5 0
## cg03770217 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 0
## cg07935632 0.0 0.0 0.0 0.0 0.0 0.0 0.0 72.0 35.5 35
## cg14679463 0.0 0.0 0.0 0.0 35.5 0.0 79.0 0.0 35.5 91
## cg09467248 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 0
## cg13336515 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg25979005 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35
## cg13970113 35.5 0.0 35.5 35.5 35.5 0.0 35.5 0.0 35.5 35
## cg17826980 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 0
## cg25934997 35.5 35.5 0.0 0.0 0.0 0.0 35.5 35.5 35.5 0
## cg02736232 35.5 35.5 35.5 35.5 0.0 0.0 35.5 35.5 35.5 0
## cg09449232 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5 0.0 35
## cg11515284 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg21165486 35.5 0.0 35.5 35.5 0.0 0.0 35.5 35.5 35.5 35
## cg04577129 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg04255401 0.0 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg17802766 0.0 35.5 0.0 0.0 35.5 0.0 0.0 88.0 35.5 0
## cg21533994 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg26767974 35.5 0.0 35.5 35.5 0.0 0.0 35.5 35.5 35.5 35
## cg24486540 35.5 35.5 88.0 0.0 0.0 35.5 35.5 35.5 0.0 35
## iter11 iter12 iter13 iter14 iter15 iter16 iter17 iter18 iter19
## cg12451325 74.0 98.0 35.5 88.0 87.0 96.0 70 94.0 80.0
## cg08248985 79.0 92.0 0.0 73.0 81.0 95.0 35 79.0 75.0
## cg26445440 75.0 0.0 0.0 90.0 0.0 89.0 87 92.0 92.0
## cg12164242 88.0 0.0 81.0 86.0 90.0 88.0 88 93.0 0.0
## cg15630265 35.5 97.0 0.0 93.0 35.5 85.0 74 84.0 0.0
## cg09216797 84.0 84.0 0.0 0.0 99.0 99.0 75 72.0 82.0
## cg13544025 0.0 99.0 87.0 84.0 93.0 97.0 92 0.0 0.0
## cg27179424 94.0 0.0 72.0 97.0 96.0 93.0 95 0.0 0.0
## cg22152677 96.0 0.0 0.0 95.0 92.0 0.0 0 85.0 0.0
## cg12084792 86.0 0.0 0.0 81.0 91.0 91.0 85 88.0 0.0
## cg03622758 0.0 90.0 0.0 35.5 79.0 80.0 35 75.0 0.0
## cg14228710 35.5 0.0 78.0 76.0 0.0 0.0 35 91.0 72.0
## cg13559778 0.0 82.0 0.0 35.5 78.0 81.0 0 86.0 0.0
## cg07523470 80.0 96.0 0.0 100.0 35.5 74.0 0 0.0 0.0
## cg16901379 95.0 100.0 76.0 91.0 0.0 98.0 0 97.0 0.0
## cg08571304 35.5 81.0 0.0 35.5 76.0 71.0 0 80.0 0.0
## cg04684637 35.5 87.0 77.0 83.0 0.0 94.0 0 0.0 0.0
## cg12546646 0.0 86.0 0.0 0.0 35.5 76.0 0 87.0 0.0
## cg20836795 35.5 95.0 35.5 0.0 80.0 86.0 0 73.0 0.0
## cg20189782 0.0 94.0 0.0 82.0 0.0 75.0 0 0.0 0.0
## cg27051815 99.0 0.0 97.0 0.0 100.0 0.0 97 0.0 0.0
## cg00970981 35.5 91.0 0.0 0.0 0.0 77.0 0 35.5 0.0
## cg12747056 85.0 0.0 85.0 0.0 0.0 100.0 91 0.0 0.0
## cg02988288 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg14527110 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg02966936 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg07175985 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg12220370 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg14490520 35.5 0.0 35.5 35.5 0.0 35.5 35 35.5 35.5
## cg13566279 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg06184251 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg03770217 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg07935632 0.0 93.0 0.0 0.0 0.0 0.0 35 76.0 0.0
## cg14679463 35.5 0.0 35.5 35.5 35.5 0.0 35 35.5 0.0
## cg09467248 35.5 35.5 35.5 35.5 35.5 35.5 35 0.0 35.5
## cg13336515 35.5 0.0 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg25979005 35.5 35.5 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg13970113 0.0 35.5 0.0 35.5 35.5 35.5 35 35.5 0.0
## cg17826980 35.5 0.0 35.5 0.0 35.5 35.5 35 35.5 35.5
## cg25934997 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg02736232 35.5 0.0 0.0 35.5 35.5 35.5 35 0.0 35.5
## cg09449232 35.5 0.0 35.5 35.5 35.5 35.5 0 35.5 35.5
## cg11515284 35.5 0.0 35.5 0.0 0.0 35.5 0 35.5 35.5
## cg21165486 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg04577129 35.5 35.5 0.0 35.5 0.0 35.5 35 35.5 35.5
## cg04255401 35.5 0.0 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg17802766 35.5 0.0 35.5 85.0 0.0 0.0 77 0.0 35.5
## cg21533994 35.5 35.5 35.5 0.0 0.0 35.5 35 35.5 0.0
## cg26767974 35.5 35.5 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg24486540 35.5 35.5 35.5 0.0 0.0 35.5 35 35.5 35.5
## iter20 iter21 iter22 iter23 iter24 iter25 iter26 iter27 iter28
## cg12451325 83 91.0 99.0 88.0 75.0 77 78.0 90.0 79.0
## cg08248985 75 75.0 92.0 83.0 86.0 89 77.0 35.5 35.5
## cg26445440 70 93.0 96.0 0.0 97.0 73 88.0 85.0 95.0
## cg12164242 91 88.0 0.0 87.0 95.0 78 0.0 86.0 86.0
## cg15630265 35 80.0 98.0 79.0 89.0 72 0.0 76.0 78.0
## cg09216797 35 85.0 76.0 99.0 0.0 0 82.0 96.0 0.0
## cg13544025 89 0.0 0.0 85.0 88.0 86 0.0 94.0 0.0
## cg27179424 93 95.0 97.0 94.0 93.0 96 92.0 92.0 0.0
## cg22152677 72 90.0 0.0 89.0 76.0 87 35.5 0.0 0.0
## cg12084792 84 89.0 95.0 75.0 87.0 82 0.0 83.0 91.0
## cg03622758 35 35.5 79.0 72.0 35.5 35 0.0 73.0 0.0
## cg14228710 74 86.0 0.0 0.0 0.0 80 89.0 88.0 35.5
## cg13559778 0 0.0 94.0 81.0 35.5 0 0.0 84.0 0.0
## cg07523470 0 0.0 90.0 0.0 99.0 0 0.0 0.0 0.0
## cg16901379 88 0.0 0.0 93.0 0.0 90 0.0 95.0 0.0
## cg08571304 0 0.0 72.0 35.5 35.5 0 0.0 35.5 76.0
## cg04684637 0 0.0 84.0 86.0 0.0 35 0.0 80.0 0.0
## cg12546646 35 35.5 86.0 77.0 35.5 35 0.0 72.0 35.5
## cg20836795 0 0.0 87.0 71.0 35.5 0 0.0 35.5 0.0
## cg20189782 0 0.0 88.0 35.5 82.0 83 0.0 0.0 0.0
## cg27051815 94 100.0 0.0 98.0 100.0 92 0.0 0.0 96.0
## cg00970981 35 0.0 75.0 35.5 0.0 35 35.5 35.5 35.5
## cg12747056 95 0.0 0.0 100.0 92.0 81 0.0 98.0 0.0
## cg02988288 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg14527110 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg02966936 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg07175985 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg12220370 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg14490520 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg13566279 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg06184251 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg03770217 35 35.5 35.5 35.5 35.5 35 35.5 35.5 0.0
## cg07935632 35 77.0 93.0 80.0 0.0 35 35.5 87.0 0.0
## cg14679463 35 35.5 0.0 35.5 72.0 35 0.0 0.0 35.5
## cg09467248 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg13336515 35 35.5 35.5 35.5 35.5 35 35.5 35.5 0.0
## cg25979005 35 35.5 35.5 35.5 35.5 35 35.5 35.5 0.0
## cg13970113 35 35.5 35.5 35.5 35.5 35 0.0 35.5 35.5
## cg17826980 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg25934997 35 35.5 35.5 35.5 35.5 35 35.5 35.5 35.5
## cg02736232 35 35.5 35.5 35.5 35.5 35 35.5 35.5 0.0
## cg09449232 35 35.5 35.5 35.5 35.5 0 35.5 35.5 35.5
## cg11515284 35 35.5 35.5 35.5 35.5 35 35.5 35.5 0.0
## cg21165486 35 35.5 35.5 35.5 35.5 0 0.0 0.0 0.0
## cg04577129 35 35.5 35.5 35.5 35.5 35 0.0 35.5 0.0
## cg04255401 35 35.5 35.5 35.5 35.5 0 35.5 35.5 35.5
## cg17802766 71 83.0 0.0 35.5 0.0 35 0.0 0.0 35.5
## cg21533994 35 0.0 35.5 35.5 0.0 35 35.5 0.0 35.5
## cg26767974 0 35.5 35.5 35.5 0.0 35 0.0 35.5 35.5
## cg24486540 35 0.0 83.0 0.0 35.5 35 35.5 78.0 0.0
## iter29 iter30 iter31 iter32 iter33 iter34 iter35 iter36 iter37
## cg12451325 90.0 79 92.0 99.0 93.0 97.0 74 92.0 0.0
## cg08248985 99.0 86 82.0 81.0 90.0 82.0 81 96.0 35.5
## cg26445440 77.0 96 89.0 96.0 86.0 95.0 89 79.0 0.0
## cg12164242 89.0 91 0.0 90.0 82.0 94.0 97 88.0 0.0
## cg15630265 88.0 85 80.0 35.5 87.0 90.0 90 73.0 0.0
## cg09216797 84.0 70 77.0 88.0 97.0 81.0 94 93.0 0.0
## cg13544025 0.0 95 0.0 87.0 83.0 89.0 98 86.0 0.0
## cg27179424 0.0 94 0.0 0.0 91.0 98.0 92 87.0 0.0
## cg22152677 95.0 87 95.0 94.0 94.0 0.0 93 99.0 0.0
## cg12084792 0.0 89 0.0 93.0 78.0 86.0 79 94.0 0.0
## cg03622758 0.0 82 0.0 83.0 81.0 72.0 87 35.5 72.0
## cg14228710 85.0 88 79.0 0.0 84.0 0.0 0 80.0 83.0
## cg13559778 0.0 73 0.0 84.0 35.5 84.0 35 35.5 0.0
## cg07523470 0.0 81 0.0 79.0 85.0 92.0 77 0.0 0.0
## cg16901379 92.0 0 94.0 100.0 0.0 0.0 0 97.0 0.0
## cg08571304 72.0 35 0.0 75.0 35.5 71.0 88 35.5 0.0
## cg04684637 0.0 71 0.0 35.5 0.0 0.0 78 84.0 0.0
## cg12546646 87.0 35 0.0 73.0 35.5 0.0 0 85.0 0.0
## cg20836795 0.0 72 0.0 80.0 35.5 85.0 75 82.0 0.0
## cg20189782 86.0 80 0.0 76.0 0.0 0.0 0 35.5 0.0
## cg27051815 0.0 0 96.0 0.0 96.0 0.0 0 0.0 0.0
## cg00970981 35.5 35 35.5 78.0 35.5 35.5 35 35.5 0.0
## cg12747056 0.0 97 0.0 0.0 0.0 99.0 99 100.0 0.0
## cg02988288 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg14527110 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg02966936 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg07175985 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg12220370 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg14490520 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg13566279 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg06184251 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg03770217 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg07935632 35.5 0 35.5 92.0 79.0 0.0 0 35.5 35.5
## cg14679463 35.5 0 75.0 71.0 0.0 0.0 83 0.0 0.0
## cg09467248 35.5 35 35.5 35.5 35.5 0.0 35 35.5 35.5
## cg13336515 35.5 35 0.0 35.5 35.5 35.5 35 35.5 35.5
## cg25979005 35.5 35 0.0 35.5 35.5 35.5 35 0.0 0.0
## cg13970113 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg17826980 35.5 35 35.5 35.5 35.5 35.5 0 35.5 35.5
## cg25934997 35.5 35 0.0 35.5 35.5 35.5 0 35.5 0.0
## cg02736232 35.5 35 35.5 35.5 35.5 35.5 0 35.5 35.5
## cg09449232 35.5 35 35.5 35.5 35.5 35.5 0 35.5 35.5
## cg11515284 35.5 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg21165486 35.5 35 35.5 35.5 35.5 35.5 35 35.5 0.0
## cg04577129 35.5 35 35.5 35.5 35.5 35.5 35 0.0 35.5
## cg04255401 0.0 35 35.5 35.5 35.5 35.5 35 35.5 35.5
## cg17802766 83.0 0 87.0 89.0 77.0 0.0 0 71.0 0.0
## cg21533994 35.5 35 35.5 0.0 35.5 35.5 35 0.0 35.5
## cg26767974 35.5 0 0.0 35.5 35.5 0.0 35 0.0 0.0
## cg24486540 0.0 35 35.5 35.5 0.0 35.5 0 0.0 35.5
## iter38 iter39 iter40 iter41 iter42 iter43 iter44 iter45 iter46
## cg12451325 99.0 86.0 74.0 83.0 88 78 97.0 91.0 88
## cg08248985 35.5 81.0 35.5 86.0 82 70 100.0 72.0 92
## cg26445440 0.0 82.0 87.0 99.0 80 89 0.0 88.0 86
## cg12164242 0.0 93.0 78.0 0.0 87 86 0.0 83.0 98
## cg15630265 93.0 35.5 94.0 95.0 84 84 92.0 76.0 87
## cg09216797 82.0 92.0 88.0 0.0 71 74 87.0 87.0 90
## cg13544025 0.0 95.0 98.0 0.0 94 88 93.0 90.0 99
## cg27179424 0.0 0.0 92.0 0.0 91 99 0.0 100.0 0
## cg22152677 0.0 85.0 90.0 0.0 96 82 99.0 96.0 0
## cg12084792 0.0 0.0 35.5 0.0 90 93 96.0 0.0 0
## cg03622758 95.0 72.0 35.5 0.0 74 71 98.0 35.5 94
## cg14228710 0.0 84.0 84.0 0.0 0 94 0.0 0.0 0
## cg13559778 88.0 35.5 35.5 0.0 81 75 88.0 75.0 82
## cg07523470 87.0 90.0 91.0 0.0 85 0 81.0 85.0 0
## cg16901379 0.0 0.0 0.0 0.0 93 92 0.0 92.0 0
## cg08571304 98.0 35.5 72.0 75.0 70 0 84.0 74.0 83
## cg04684637 0.0 0.0 76.0 0.0 78 0 85.0 73.0 0
## cg12546646 94.0 35.5 0.0 0.0 0 0 94.0 79.0 97
## cg20836795 85.0 0.0 35.5 0.0 86 35 86.0 35.5 89
## cg20189782 0.0 0.0 35.5 93.0 69 0 74.0 71.0 0
## cg27051815 0.0 100.0 93.0 100.0 0 0 0.0 0.0 0
## cg00970981 35.5 35.5 0.0 35.5 34 35 82.0 35.5 70
## cg12747056 0.0 0.0 95.0 0.0 97 0 0.0 95.0 0
## cg02988288 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg14527110 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg02966936 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg07175985 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg12220370 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg14490520 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg13566279 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg06184251 35.5 35.5 35.5 35.5 34 0 35.5 35.5 35
## cg03770217 35.5 35.5 35.5 35.5 34 0 35.5 35.5 35
## cg07935632 75.0 0.0 0.0 0.0 34 35 79.0 0.0 81
## cg14679463 0.0 76.0 35.5 76.0 77 0 0.0 35.5 0
## cg09467248 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg13336515 0.0 35.5 35.5 35.5 34 35 35.5 35.5 0
## cg25979005 0.0 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg13970113 92.0 35.5 35.5 35.5 34 35 35.5 35.5 72
## cg17826980 0.0 35.5 35.5 35.5 0 0 35.5 35.5 0
## cg25934997 0.0 35.5 35.5 35.5 34 35 35.5 35.5 0
## cg02736232 0.0 35.5 35.5 35.5 0 35 0.0 35.5 35
## cg09449232 35.5 0.0 35.5 35.5 34 35 35.5 35.5 35
## cg11515284 35.5 35.5 35.5 0.0 34 35 35.5 35.5 0
## cg21165486 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg04577129 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg04255401 35.5 35.5 35.5 0.0 34 35 35.5 35.5 0
## cg17802766 0.0 0.0 79.0 0.0 0 83 0.0 89.0 0
## cg21533994 35.5 35.5 0.0 35.5 34 0 35.5 0.0 35
## cg26767974 35.5 35.5 35.5 35.5 34 35 35.5 35.5 35
## cg24486540 35.5 0.0 35.5 0.0 34 35 35.5 35.5 0
## iter47 iter48 iter49 iter50 iter51 iter52 iter53 iter54 iter55
## cg12451325 94 96.0 99.0 0.0 35.5 0.0 85.0 90.0 84.0
## cg08248985 35 87.0 91.0 0.0 35.5 35.5 79.0 87.0 83.0
## cg26445440 99 82.0 93.0 0.0 83.0 0.0 97.0 77.0 92.0
## cg12164242 97 92.0 95.0 0.0 81.0 0.0 84.0 88.0 82.0
## cg15630265 92 77.0 94.0 0.0 72.0 0.0 74.0 78.0 35.5
## cg09216797 0 91.0 85.0 94.0 89.0 0.0 94.0 97.0 0.0
## cg13544025 98 94.0 90.0 0.0 90.0 0.0 89.0 96.0 0.0
## cg27179424 91 95.0 97.0 0.0 95.0 0.0 90.0 99.0 0.0
## cg22152677 0 0.0 0.0 0.0 78.0 82.0 86.0 95.0 95.0
## cg12084792 86 0.0 0.0 0.0 92.0 0.0 87.0 0.0 90.0
## cg03622758 78 86.0 35.5 35.5 0.0 0.0 76.0 73.0 0.0
## cg14228710 0 0.0 0.0 0.0 87.0 81.0 92.0 93.0 91.0
## cg13559778 81 90.0 96.0 0.0 76.0 0.0 78.0 35.5 0.0
## cg07523470 83 80.0 98.0 0.0 0.0 0.0 99.0 85.0 0.0
## cg16901379 88 93.0 0.0 0.0 75.0 0.0 95.0 0.0 86.0
## cg08571304 35 75.0 74.0 0.0 35.5 0.0 35.5 84.0 0.0
## cg04684637 82 88.0 0.0 0.0 0.0 0.0 82.0 74.0 0.0
## cg12546646 0 78.0 87.0 0.0 35.5 0.0 35.5 94.0 35.5
## cg20836795 70 81.0 72.0 0.0 0.0 0.0 35.5 35.5 0.0
## cg20189782 73 73.0 0.0 0.0 71.0 0.0 93.0 75.0 0.0
## cg27051815 0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 96.0
## cg00970981 35 35.5 76.0 0.0 35.5 0.0 35.5 92.0 35.5
## cg12747056 0 100.0 0.0 0.0 0.0 0.0 0.0 0.0 88.0
## cg02988288 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg14527110 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg02966936 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg07175985 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg12220370 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg14490520 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg13566279 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg06184251 35 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg03770217 35 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5
## cg07935632 0 89.0 0.0 0.0 0.0 0.0 75.0 76.0 85.0
## cg14679463 75 0.0 0.0 0.0 0.0 0.0 35.5 0.0 0.0
## cg09467248 35 0.0 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg13336515 35 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5
## cg25979005 35 35.5 35.5 35.5 35.5 35.5 35.5 0.0 35.5
## cg13970113 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg17826980 35 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg25934997 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg02736232 35 35.5 35.5 35.5 35.5 35.5 35.5 0.0 35.5
## cg09449232 35 0.0 0.0 0.0 35.5 35.5 35.5 35.5 35.5
## cg11515284 35 35.5 0.0 35.5 0.0 35.5 35.5 0.0 35.5
## cg21165486 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg04577129 35 35.5 35.5 0.0 35.5 35.5 0.0 35.5 0.0
## cg04255401 0 0.0 0.0 35.5 0.0 35.5 35.5 35.5 35.5
## cg17802766 0 0.0 0.0 0.0 35.5 0.0 81.0 0.0 35.5
## cg21533994 35 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg26767974 0 35.5 35.5 35.5 35.5 35.5 35.5 35.5 0.0
## cg24486540 0 35.5 71.0 35.5 35.5 35.5 35.5 35.5 35.5
## iter56 iter57 iter58 iter59 iter60 iter61 iter62 iter63 iter64
## cg12451325 85.0 83.0 74.0 93 84.0 0.0 90 85 0.0
## cg08248985 78.0 35.5 35.5 80 78.0 35.5 86 84 96.0
## cg26445440 0.0 35.5 88.0 75 97.0 0.0 78 94 0.0
## cg12164242 0.0 88.0 77.0 85 0.0 0.0 91 97 0.0
## cg15630265 0.0 35.5 78.0 77 88.0 0.0 35 89 0.0
## cg09216797 0.0 0.0 96.0 92 87.0 0.0 79 88 99.0
## cg13544025 0.0 89.0 83.0 96 0.0 0.0 93 0 0.0
## cg27179424 0.0 97.0 93.0 0 0.0 0.0 99 0 0.0
## cg22152677 0.0 86.0 89.0 0 0.0 0.0 0 92 0.0
## cg12084792 0.0 35.5 86.0 90 0.0 0.0 96 99 0.0
## cg03622758 0.0 0.0 35.5 91 0.0 35.5 72 35 0.0
## cg14228710 84.0 71.0 92.0 0 92.0 35.5 0 0 0.0
## cg13559778 0.0 35.5 35.5 97 0.0 0.0 82 82 0.0
## cg07523470 0.0 0.0 95.0 72 0.0 0.0 92 0 0.0
## cg16901379 0.0 94.0 82.0 0 0.0 0.0 84 96 0.0
## cg08571304 0.0 0.0 75.0 35 0.0 0.0 35 81 0.0
## cg04684637 0.0 82.0 0.0 81 0.0 0.0 0 75 0.0
## cg12546646 0.0 0.0 85.0 88 0.0 0.0 71 95 0.0
## cg20836795 0.0 35.5 72.0 89 0.0 0.0 35 78 0.0
## cg20189782 0.0 0.0 73.0 79 0.0 0.0 88 0 0.0
## cg27051815 0.0 99.0 0.0 0 0.0 89.0 95 0 0.0
## cg00970981 0.0 0.0 35.5 83 71.0 0.0 35 76 0.0
## cg12747056 0.0 91.0 91.0 0 0.0 85.0 87 93 0.0
## cg02988288 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg14527110 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg02966936 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg07175985 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg12220370 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg14490520 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg13566279 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg06184251 35.5 35.5 35.5 0 35.5 35.5 35 35 35.5
## cg03770217 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg07935632 0.0 35.5 0.0 87 86.0 0.0 80 35 0.0
## cg14679463 0.0 35.5 35.5 82 0.0 0.0 35 0 0.0
## cg09467248 35.5 35.5 35.5 0 35.5 35.5 35 35 35.5
## cg13336515 35.5 35.5 0.0 35 35.5 35.5 35 0 35.5
## cg25979005 35.5 35.5 35.5 0 35.5 35.5 35 0 35.5
## cg13970113 0.0 0.0 35.5 35 35.5 0.0 35 35 0.0
## cg17826980 35.5 35.5 35.5 0 35.5 35.5 35 0 35.5
## cg25934997 0.0 35.5 35.5 0 35.5 35.5 35 35 0.0
## cg02736232 35.5 35.5 35.5 35 0.0 35.5 35 35 35.5
## cg09449232 0.0 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg11515284 35.5 35.5 35.5 35 35.5 35.5 35 35 35.5
## cg21165486 35.5 35.5 35.5 35 35.5 35.5 35 35 0.0
## cg04577129 0.0 35.5 35.5 35 0.0 35.5 35 35 0.0
## cg04255401 35.5 35.5 35.5 35 35.5 0.0 0 35 35.5
## cg17802766 87.0 35.5 76.0 0 83.0 0.0 75 0 0.0
## cg21533994 35.5 35.5 0.0 0 35.5 35.5 0 35 35.5
## cg26767974 35.5 0.0 35.5 35 35.5 35.5 35 0 0.0
## cg24486540 35.5 35.5 0.0 35 76.0 35.5 0 35 35.5
## iter65 iter66 iter67 iter68 iter69 iter70 iter71 iter72 iter73
## cg12451325 97 87 90 97 95.0 92 85.0 91 0.0
## cg08248985 81 82 79 76 78.0 74 35.5 77 0.0
## cg26445440 93 97 81 0 92.0 35 79.0 81 0.0
## cg12164242 98 98 0 91 98.0 91 83.0 0 0.0
## cg15630265 96 92 76 73 35.5 82 73.0 94 0.0
## cg09216797 35 73 74 89 89.0 79 0.0 93 0.0
## cg13544025 0 94 0 90 96.0 98 84.0 97 0.0
## cg27179424 0 0 99 96 91.0 94 90.0 96 0.0
## cg22152677 0 0 87 94 0.0 88 92.0 0 0.0
## cg12084792 89 0 78 92 100.0 0 35.5 76 0.0
## cg03622758 35 84 35 74 80.0 35 35.5 78 0.0
## cg14228710 0 0 82 0 85.0 0 80.0 86 0.0
## cg13559778 35 78 0 78 76.0 35 35.5 73 35.5
## cg07523470 99 95 0 81 0.0 93 0.0 0 0.0
## cg16901379 0 0 0 95 94.0 0 93.0 90 0.0
## cg08571304 35 76 0 35 79.0 72 35.5 35 0.0
## cg04684637 94 0 0 79 0.0 71 0.0 88 0.0
## cg12546646 92 0 80 77 83.0 81 0.0 35 0.0
## cg20836795 85 0 0 84 82.0 35 35.5 0 0.0
## cg20189782 95 93 0 35 86.0 84 0.0 79 0.0
## cg27051815 0 0 98 99 99.0 99 98.0 0 0.0
## cg00970981 35 35 35 75 71.0 35 35.5 35 35.5
## cg12747056 0 0 97 98 0.0 89 89.0 0 0.0
## cg02988288 35 35 35 35 35.5 35 35.5 35 35.5
## cg14527110 35 35 35 35 35.5 35 35.5 35 35.5
## cg02966936 35 35 35 35 35.5 35 35.5 35 35.5
## cg07175985 35 35 35 35 35.5 35 35.5 35 35.5
## cg12220370 35 35 35 35 35.5 35 35.5 35 35.5
## cg14490520 35 35 35 35 35.5 35 35.5 35 35.5
## cg13566279 35 35 35 35 35.5 35 35.5 35 0.0
## cg06184251 35 35 35 35 35.5 35 35.5 35 35.5
## cg03770217 35 35 35 35 35.5 35 35.5 35 0.0
## cg07935632 0 0 35 82 81.0 35 72.0 74 0.0
## cg14679463 0 91 83 0 77.0 75 71.0 0 0.0
## cg09467248 35 35 35 35 35.5 35 35.5 35 0.0
## cg13336515 35 35 35 35 35.5 35 35.5 35 35.5
## cg25979005 35 35 35 35 35.5 35 35.5 35 0.0
## cg13970113 35 35 35 35 35.5 35 35.5 35 0.0
## cg17826980 35 35 35 35 0.0 35 35.5 35 35.5
## cg25934997 35 35 35 35 35.5 35 35.5 35 35.5
## cg02736232 35 0 35 35 35.5 35 35.5 35 35.5
## cg09449232 35 35 35 35 35.5 35 35.5 35 35.5
## cg11515284 35 0 35 35 35.5 35 35.5 35 35.5
## cg21165486 35 35 35 35 35.5 35 0.0 35 0.0
## cg04577129 35 35 35 35 35.5 35 35.5 35 0.0
## cg04255401 35 0 35 35 35.5 35 35.5 35 0.0
## cg17802766 0 0 94 0 0.0 83 0.0 87 0.0
## cg21533994 35 35 35 0 0.0 0 35.5 0 35.5
## cg26767974 35 35 35 35 0.0 35 0.0 35 35.5
## cg24486540 35 35 35 35 0.0 35 35.5 35 35.5
## iter74 iter75 iter76 iter77 iter78 iter79 iter80 iter81 iter82
## cg12451325 82 94.0 35.5 35.5 78.0 79.0 87.0 91.0 90.0
## cg08248985 84 95.0 84.0 74.0 77.0 35.5 82.0 78.0 86.0
## cg26445440 90 97.0 89.0 94.0 76.0 94.0 0.0 95.0 96.0
## cg12164242 89 0.0 0.0 78.0 90.0 87.0 88.0 83.0 93.0
## cg15630265 87 84.0 35.5 83.0 75.0 80.0 35.5 94.0 88.0
## cg09216797 97 88.0 92.0 84.0 91.0 0.0 97.0 72.0 92.0
## cg13544025 93 0.0 0.0 0.0 96.0 96.0 94.0 88.0 94.0
## cg27179424 98 100.0 100.0 0.0 0.0 90.0 95.0 0.0 0.0
## cg22152677 99 96.0 76.0 86.0 80.0 82.0 96.0 86.0 99.0
## cg12084792 96 98.0 0.0 0.0 0.0 89.0 86.0 92.0 98.0
## cg03622758 74 73.0 0.0 0.0 84.0 35.5 85.0 35.5 79.0
## cg14228710 78 0.0 80.0 85.0 35.5 35.5 0.0 93.0 85.0
## cg13559778 35 35.5 0.0 0.0 83.0 81.0 79.0 35.5 0.0
## cg07523470 92 91.0 0.0 0.0 0.0 99.0 35.5 89.0 0.0
## cg16901379 0 0.0 0.0 0.0 92.0 85.0 92.0 0.0 0.0
## cg08571304 35 35.5 0.0 0.0 0.0 75.0 81.0 0.0 73.0
## cg04684637 73 79.0 0.0 0.0 0.0 0.0 0.0 81.0 91.0
## cg12546646 0 87.0 35.5 0.0 0.0 35.5 76.0 0.0 84.0
## cg20836795 0 74.0 0.0 0.0 0.0 35.5 83.0 0.0 0.0
## cg20189782 0 90.0 0.0 0.0 0.0 83.0 35.5 0.0 97.0
## cg27051815 0 0.0 0.0 0.0 100.0 97.0 100.0 0.0 0.0
## cg00970981 35 35.5 35.5 35.5 35.5 35.5 89.0 35.5 35.5
## cg12747056 0 0.0 90.0 0.0 0.0 92.0 0.0 0.0 0.0
## cg02988288 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg14527110 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg02966936 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg07175985 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg12220370 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg14490520 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg13566279 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg06184251 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg03770217 35 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5
## cg07935632 83 0.0 35.5 35.5 35.5 0.0 35.5 75.0 78.0
## cg14679463 80 82.0 0.0 0.0 0.0 0.0 35.5 76.0 76.0
## cg09467248 35 35.5 35.5 0.0 35.5 0.0 35.5 0.0 35.5
## cg13336515 35 0.0 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg25979005 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg13970113 35 77.0 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg17826980 35 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5
## cg25934997 35 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5
## cg02736232 35 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5
## cg09449232 35 0.0 35.5 35.5 35.5 0.0 35.5 0.0 35.5
## cg11515284 0 0.0 35.5 35.5 35.5 35.5 35.5 0.0 35.5
## cg21165486 35 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5
## cg04577129 35 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5
## cg04255401 0 0.0 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg17802766 0 0.0 35.5 0.0 0.0 0.0 0.0 0.0 0.0
## cg21533994 35 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5
## cg26767974 35 35.5 35.5 0.0 35.5 0.0 35.5 35.5 35.5
## cg24486540 0 0.0 0.0 35.5 0.0 35.5 0.0 74.0 0.0
## iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90 iter91
## cg12451325 92 98.0 91.0 87.0 95.0 82.0 91.0 91.0 92.0
## cg08248985 90 88.0 35.5 86.0 94.0 35.5 73.0 78.0 87.0
## cg26445440 98 92.0 0.0 83.0 78.0 0.0 98.0 92.0 91.0
## cg12164242 86 97.0 85.0 93.0 85.0 92.0 89.0 88.0 94.0
## cg15630265 91 85.0 96.0 92.0 84.0 35.5 79.0 75.0 93.0
## cg09216797 88 80.0 0.0 79.0 75.0 87.0 0.0 87.0 89.0
## cg13544025 94 91.0 92.0 0.0 0.0 94.0 0.0 77.0 97.0
## cg27179424 97 100.0 86.0 90.0 0.0 0.0 97.0 95.0 99.0
## cg22152677 93 95.0 0.0 96.0 0.0 93.0 88.0 83.0 0.0
## cg12084792 0 99.0 0.0 95.0 0.0 0.0 0.0 0.0 88.0
## cg03622758 80 86.0 35.5 71.0 0.0 0.0 0.0 35.5 82.0
## cg14228710 0 0.0 35.5 84.0 98.0 75.0 86.0 79.0 0.0
## cg13559778 76 77.0 35.5 35.5 0.0 0.0 0.0 35.5 76.0
## cg07523470 95 96.0 0.0 97.0 0.0 0.0 0.0 81.0 86.0
## cg16901379 96 0.0 87.0 0.0 0.0 95.0 0.0 93.0 0.0
## cg08571304 83 76.0 35.5 35.5 0.0 0.0 35.5 35.5 80.0
## cg04684637 89 75.0 35.5 35.5 74.0 81.0 0.0 72.0 81.0
## cg12546646 0 0.0 73.0 88.0 86.0 0.0 72.0 74.0 85.0
## cg20836795 0 74.0 0.0 82.0 0.0 35.5 0.0 35.5 35.5
## cg20189782 78 83.0 0.0 76.0 0.0 74.0 0.0 35.5 96.0
## cg27051815 0 0.0 99.0 100.0 0.0 99.0 99.0 0.0 0.0
## cg00970981 72 35.5 35.5 72.0 35.5 0.0 0.0 35.5 35.5
## cg12747056 99 0.0 0.0 0.0 92.0 0.0 0.0 0.0 0.0
## cg02988288 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg14527110 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg02966936 35 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5
## cg07175985 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg12220370 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg14490520 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg13566279 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg06184251 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg03770217 35 35.5 35.5 35.5 35.5 35.5 35.5 0.0 35.5
## cg07935632 0 81.0 0.0 0.0 35.5 0.0 0.0 0.0 0.0
## cg14679463 84 0.0 0.0 74.0 76.0 35.5 77.0 35.5 84.0
## cg09467248 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5
## cg13336515 35 35.5 35.5 35.5 35.5 35.5 35.5 35.5 0.0
## cg25979005 35 35.5 35.5 35.5 35.5 35.5 35.5 0.0 35.5
## cg13970113 35 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5
## cg17826980 35 0.0 35.5 35.5 35.5 35.5 35.5 35.5 0.0
## cg25934997 35 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5
## cg02736232 0 35.5 35.5 35.5 0.0 35.5 35.5 0.0 35.5
## cg09449232 35 35.5 0.0 35.5 35.5 35.5 35.5 35.5 0.0
## cg11515284 35 35.5 0.0 35.5 35.5 35.5 35.5 35.5 0.0
## cg21165486 35 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35.5
## cg04577129 35 35.5 0.0 35.5 0.0 0.0 35.5 0.0 35.5
## cg04255401 35 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35.5
## cg17802766 0 0.0 89.0 0.0 89.0 76.0 82.0 89.0 0.0
## cg21533994 35 0.0 35.5 35.5 35.5 35.5 35.5 35.5 0.0
## cg26767974 35 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5
## cg24486540 35 35.5 0.0 35.5 35.5 35.5 35.5 35.5 0.0
## iter92 iter93 iter94 iter95 iter96 iter97 iter98 iter99 iter100
## cg12451325 77.0 74.0 93.0 74.0 71.0 87.0 95.0 94.0 98
## cg08248985 85.0 81.0 83.0 35.5 89.0 77.0 94.0 93.0 86
## cg26445440 97.0 78.0 35.5 0.0 85.0 79.0 97.0 0.0 82
## cg12164242 86.0 94.0 88.0 0.0 86.0 0.0 99.0 92.0 92
## cg15630265 76.0 35.5 85.0 0.0 81.0 72.0 80.0 88.0 95
## cg09216797 91.0 0.0 95.0 0.0 97.0 92.0 83.0 80.0 0
## cg13544025 92.0 93.0 79.0 0.0 91.0 94.0 92.0 97.0 97
## cg27179424 99.0 84.0 97.0 0.0 96.0 93.0 100.0 98.0 0
## cg22152677 0.0 0.0 99.0 35.5 92.0 98.0 98.0 87.0 85
## cg12084792 88.0 98.0 81.0 0.0 88.0 35.5 85.0 90.0 0
## cg03622758 35.5 35.5 73.0 0.0 83.0 73.0 35.5 82.0 74
## cg14228710 73.0 75.0 80.0 79.0 0.0 35.5 0.0 0.0 89
## cg13559778 35.5 0.0 76.0 0.0 35.5 0.0 84.0 81.0 75
## cg07523470 90.0 85.0 35.5 0.0 76.0 0.0 88.0 35.5 90
## cg16901379 81.0 79.0 0.0 0.0 90.0 84.0 0.0 99.0 94
## cg08571304 35.5 35.5 35.5 0.0 35.5 35.5 77.0 35.5 35
## cg04684637 35.5 35.5 35.5 0.0 77.0 0.0 78.0 89.0 93
## cg12546646 0.0 35.5 84.0 0.0 0.0 35.5 0.0 83.0 87
## cg20836795 0.0 35.5 75.0 0.0 35.5 85.0 81.0 84.0 35
## cg20189782 89.0 0.0 35.5 0.0 78.0 0.0 86.0 78.0 0
## cg27051815 96.0 95.0 100.0 0.0 0.0 96.0 0.0 0.0 96
## cg00970981 0.0 35.5 71.0 0.0 72.0 0.0 74.0 35.5 35
## cg12747056 0.0 0.0 94.0 0.0 93.0 99.0 0.0 100.0 0
## cg02988288 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg14527110 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg02966936 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg07175985 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg12220370 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg14490520 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg13566279 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg06184251 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg03770217 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg07935632 35.5 0.0 82.0 0.0 0.0 35.5 0.0 86.0 35
## cg14679463 35.5 72.0 72.0 0.0 35.5 35.5 93.0 75.0 0
## cg09467248 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35
## cg13336515 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35.5 35
## cg25979005 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg13970113 35.5 35.5 35.5 0.0 35.5 35.5 35.5 35.5 35
## cg17826980 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg25934997 35.5 35.5 35.5 35.5 35.5 0.0 35.5 35.5 35
## cg02736232 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35.5 35
## cg09449232 0.0 0.0 35.5 35.5 35.5 35.5 35.5 35.5 0
## cg11515284 0.0 35.5 0.0 35.5 0.0 35.5 35.5 35.5 35
## cg21165486 35.5 35.5 0.0 0.0 35.5 35.5 35.5 0.0 35
## cg04577129 35.5 35.5 35.5 0.0 0.0 35.5 35.5 35.5 35
## cg04255401 0.0 35.5 35.5 35.5 0.0 35.5 35.5 35.5 0
## cg17802766 0.0 0.0 0.0 0.0 35.5 0.0 0.0 0.0 83
## cg21533994 35.5 35.5 35.5 35.5 35.5 35.5 35.5 0.0 35
## cg26767974 35.5 35.5 35.5 0.0 35.5 35.5 35.5 0.0 35
## cg24486540 0.0 35.5 0.0 35.5 0.0 0.0 35.5 35.5 0
## total_rank
## cg12451325 7904.5
## cg08248985 7125.5
## cg26445440 6837.5
## cg12164242 6692.0
## cg15630265 6592.5
## cg09216797 6562.0
## cg13544025 6164.0
## cg27179424 5956.0
## cg22152677 5548.0
## cg12084792 4928.0
## cg03622758 4780.0
## cg14228710 4440.5
## cg13559778 4328.5
## cg07523470 4313.5
## cg16901379 4287.0
## cg08571304 4010.5
## cg04684637 3898.0
## cg12546646 3867.0
## cg20836795 3731.5
## cg20189782 3718.5
## cg27051815 3700.0
## cg00970981 3618.5
## cg12747056 3568.0
## cg02988288 3538.0
## cg14527110 3538.0
## cg02966936 3502.5
## cg07175985 3502.5
## cg12220370 3502.5
## cg14490520 3431.5
## cg13566279 3396.0
## cg06184251 3362.0
## cg03770217 3219.5
## cg07935632 3202.0
## cg14679463 3196.0
## cg09467248 3077.5
## cg13336515 3077.5
## cg25979005 3077.5
## cg13970113 3069.5
## cg17826980 3010.0
## cg25934997 2936.5
## cg02736232 2902.5
## cg09449232 2865.5
## cg11515284 2865.5
## cg21165486 2864.0
## cg04577129 2828.0
## cg04255401 2760.5
## cg17802766 2732.5
## cg21533994 2724.5
## cg26767974 2688.0
## cg24486540 2662.0write.table(meth_features_comp2_final,file="Comp2_METH_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
gen_features_comp1_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),gen_features_comp1)
rownames(gen_features_comp1_final)<-gen_features_comp1_final$GENE
gen_features_comp1_final$GENE<-NULL
gen_features_comp1_final[is.na(gen_features_comp1_final)]<-0
gen_features_comp1_final$total_rank<-rowSums(gen_features_comp1_final)
gen_features_comp1_final<-gen_features_comp1_final[order(-gen_features_comp1_final$total_rank),]
print(head(gen_features_comp1_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10
## rs13279576_A 18 0 40.0 39 39 17.5 0 40 18 18
## rs7931183_A 0 39 0.0 40 40 39.0 18 37 40 0
## rs10837562_G 18 18 0.0 37 18 36.0 38 36 37 40
## rs9296990_A 40 0 0.0 18 38 17.5 18 0 18 18
## rs2331992_G 39 0 0.0 0 0 0.0 39 0 18 18
## rs12476415_G 18 18 35.5 0 18 0.0 0 18 0 18
## rs7430710_A 18 0 17.5 18 0 17.5 18 0 18 18
## rs11257386_A 18 0 0.0 18 18 0.0 40 0 0 0
## rs2149733_A 18 0 0.0 18 0 17.5 0 18 0 18
## rs2168477_A 18 0 17.5 18 0 17.5 0 18 0 0
## rs10412466_G 18 0 39.0 0 0 35.0 0 18 0 38
## rs694625_A 0 18 17.5 18 36 0.0 0 0 0 18
## rs11150589_A 18 18 17.5 18 18 0.0 18 0 0 0
## rs16825228_G 0 0 35.5 0 18 0.0 0 0 0 18
## rs12005670_A 18 18 0.0 18 0 0.0 0 18 18 0
## rs12598978_A 18 18 17.5 18 0 0.0 18 0 0 0
## rs10405944_G 0 0 17.5 0 18 17.5 0 0 18 18
## rs12629469_A 0 0 38.0 18 37 0.0 0 18 0 0
## rs10063667_A 0 18 0.0 0 18 17.5 18 18 0 0
## rs8093884_A 18 37 0.0 18 18 0.0 18 0 0 0
## rs10795908_G 0 38 0.0 0 0 0.0 18 0 0 0
## rs4821456_G 18 0 0.0 0 0 0.0 0 0 0 36
## rs13058433_G 0 18 0.0 0 0 0.0 0 0 38 0
## rs7807747_A 0 0 0.0 18 0 0.0 18 18 0 18
## rs12679812_A 0 0 0.0 0 0 0.0 0 18 18 0
## rs11981000_G 0 0 0.0 0 18 0.0 18 18 18 0
## rs10050725_G 0 0 0.0 0 0 38.0 0 38 0 18
## rs4716858_A 0 40 0.0 0 0 0.0 0 0 39 18
## rs7840855_G 18 0 17.5 0 0 17.5 18 0 18 0
## rs818441_A 18 0 17.5 18 0 17.5 0 0 18 0
## rs4282978_A 0 0 17.5 0 0 0.0 0 39 0 0
## rs635070_A 0 0 0.0 0 0 0.0 18 0 18 0
## rs12794303_G 0 0 0.0 0 0 17.5 0 0 0 18
## rs9291002_A 0 0 0.0 0 0 17.5 18 0 0 0
## rs4932545_G 0 0 0.0 18 0 0.0 18 18 0 0
## rs742502_G 0 18 0.0 0 0 0.0 0 0 18 0
## rs1016090_G 0 0 0.0 0 0 0.0 0 0 0 0
## rs1732581_A 18 0 17.5 0 0 0.0 0 0 0 0
## rs750064_G 0 0 17.5 0 0 0.0 0 0 0 0
## rs4961252_G 0 0 0.0 0 18 17.5 0 0 0 0
## rs933881_G 0 0 0.0 0 18 17.5 0 0 0 18
## rs7327037_G 0 0 0.0 0 18 0.0 0 0 0 0
## rs1882153_A 18 0 17.5 0 0 0.0 0 0 0 0
## rs2835695_G 0 0 0.0 0 0 0.0 18 0 0 0
## rs11218557_G 18 0 17.5 18 0 0.0 0 0 0 0
## rs3095301_G 0 18 0.0 0 0 0.0 18 0 0 0
## rs3095302_A 0 18 0.0 0 0 0.0 18 0 0 0
## rs3131003_A 0 18 0.0 0 0 0.0 18 0 0 0
## rs7725574_C 0 18 0.0 0 0 0.0 0 0 36 0
## rs7912364_C 0 0 17.5 18 0 17.5 0 0 0 18
## iter11 iter12 iter13 iter14 iter15 iter16 iter17 iter18
## rs13279576_A 36 18 18 40 39 18 36 40
## rs7931183_A 18 0 40 39 18 38 37 0
## rs10837562_G 40 38 18 0 0 39 40 18
## rs9296990_A 0 40 39 18 0 18 18 18
## rs2331992_G 0 18 0 18 0 0 0 0
## rs12476415_G 18 36 0 18 0 0 18 0
## rs7430710_A 18 18 18 18 18 18 18 18
## rs11257386_A 0 0 0 0 0 0 18 0
## rs2149733_A 18 0 18 0 18 18 18 18
## rs2168477_A 18 18 0 18 18 0 0 0
## rs10412466_G 0 0 18 0 0 0 0 36
## rs694625_A 0 37 0 0 0 0 18 0
## rs11150589_A 18 0 18 0 0 18 18 0
## rs16825228_G 0 18 0 18 0 0 18 0
## rs12005670_A 18 18 0 18 0 18 18 0
## rs12598978_A 18 0 18 0 0 18 18 0
## rs10405944_G 18 0 0 0 0 18 0 18
## rs12629469_A 18 39 0 0 0 0 0 0
## rs10063667_A 18 0 18 0 18 18 18 18
## rs8093884_A 0 18 0 18 0 18 0 0
## rs10795908_G 0 0 0 0 0 0 18 0
## rs4821456_G 0 0 0 0 0 0 18 0
## rs13058433_G 18 0 0 18 0 0 18 18
## rs7807747_A 0 0 0 0 0 0 18 0
## rs12679812_A 18 0 0 18 0 0 18 0
## rs11981000_G 0 0 0 0 40 40 38 0
## rs10050725_G 18 0 18 0 0 18 18 18
## rs4716858_A 0 0 0 0 0 0 18 0
## rs7840855_G 0 0 0 0 0 18 0 18
## rs818441_A 18 0 0 18 0 0 18 0
## rs4282978_A 0 0 0 0 0 0 18 37
## rs635070_A 0 0 0 18 0 0 0 0
## rs12794303_G 18 18 0 18 0 0 18 0
## rs9291002_A 0 0 0 0 0 0 18 0
## rs4932545_G 0 0 0 0 0 18 18 0
## rs742502_G 0 0 0 18 0 0 0 18
## rs1016090_G 0 0 18 0 18 0 18 18
## rs1732581_A 0 0 0 0 0 18 0 0
## rs750064_G 0 0 0 0 0 0 0 0
## rs4961252_G 0 0 0 18 36 0 0 0
## rs933881_G 0 0 0 0 0 0 0 0
## rs7327037_G 0 0 0 0 0 0 0 0
## rs1882153_A 0 0 0 0 0 18 0 0
## rs2835695_G 0 0 18 0 38 18 0 0
## rs11218557_G 0 0 0 0 18 0 0 0
## rs3095301_G 0 18 0 0 0 0 0 0
## rs3095302_A 0 18 0 0 0 0 0 0
## rs3131003_A 0 18 0 0 0 0 0 0
## rs7725574_C 0 0 0 0 0 0 0 0
## rs7912364_C 0 0 0 0 0 18 0 18
## iter19 iter20 iter21 iter22 iter23 iter24 iter25 iter26
## rs13279576_A 18 38 39 36 18 18 0 0.0
## rs7931183_A 18 18 18 40 40 18 18 36.0
## rs10837562_G 38 18 0 0 0 0 36 0.0
## rs9296990_A 39 0 0 18 0 0 18 0.0
## rs2331992_G 18 0 18 39 0 0 0 0.0
## rs12476415_G 0 18 37 0 18 40 18 0.0
## rs7430710_A 18 18 18 0 18 18 18 18.0
## rs11257386_A 37 18 40 37 18 36 0 0.0
## rs2149733_A 18 18 18 0 0 18 18 0.0
## rs2168477_A 0 0 18 18 0 18 18 0.0
## rs10412466_G 0 37 0 0 18 0 0 0.0
## rs694625_A 0 40 18 38 18 18 0 0.0
## rs11150589_A 18 0 18 18 0 0 0 0.0
## rs16825228_G 0 18 18 0 0 39 18 0.0
## rs12005670_A 0 0 18 18 18 0 18 0.0
## rs12598978_A 18 0 18 18 0 0 0 0.0
## rs10405944_G 18 0 0 18 0 18 18 18.0
## rs12629469_A 18 0 0 0 0 0 0 0.0
## rs10063667_A 18 18 0 0 0 0 18 0.0
## rs8093884_A 0 0 0 18 18 0 18 18.0
## rs10795908_G 18 18 38 0 18 18 0 0.0
## rs4821456_G 0 18 0 0 0 0 0 0.0
## rs13058433_G 0 36 0 18 0 0 0 39.5
## rs7807747_A 0 18 18 18 0 0 0 18.0
## rs12679812_A 18 0 0 0 0 0 18 0.0
## rs11981000_G 0 18 0 0 39 0 0 0.0
## rs10050725_G 18 0 0 0 18 0 0 0.0
## rs4716858_A 18 39 0 0 0 0 0 0.0
## rs7840855_G 0 0 0 0 0 0 18 18.0
## rs818441_A 0 18 0 0 0 18 18 0.0
## rs4282978_A 0 18 18 0 0 0 0 0.0
## rs635070_A 0 0 0 18 0 18 18 18.0
## rs12794303_G 18 18 18 0 18 18 0 0.0
## rs9291002_A 0 18 0 18 0 0 0 0.0
## rs4932545_G 0 0 0 18 0 0 18 0.0
## rs742502_G 0 18 0 18 0 0 0 39.5
## rs1016090_G 0 0 0 0 0 0 0 0.0
## rs1732581_A 0 18 18 0 0 18 0 0.0
## rs750064_G 0 0 36 18 18 0 0 0.0
## rs4961252_G 18 0 0 0 0 18 0 18.0
## rs933881_G 40 0 0 0 0 0 0 0.0
## rs7327037_G 36 0 0 0 0 18 0 18.0
## rs1882153_A 0 18 18 0 0 0 0 0.0
## rs2835695_G 0 0 0 18 0 0 0 0.0
## rs11218557_G 0 18 18 0 0 0 0 0.0
## rs3095301_G 0 0 0 0 18 0 0 18.0
## rs3095302_A 0 0 0 0 18 0 0 18.0
## rs3131003_A 0 0 0 0 18 0 0 18.0
## rs7725574_C 0 0 0 0 0 0 18 0.0
## rs7912364_C 0 0 0 0 0 18 0 0.0
## iter27 iter28 iter29 iter30 iter31 iter32 iter33 iter34
## rs13279576_A 0 38 40 18 37 40 39 0
## rs7931183_A 40 39 0 40 18 0 36 39
## rs10837562_G 0 18 18 39 40 37 0 18
## rs9296990_A 0 0 18 38 18 39 0 18
## rs2331992_G 38 0 0 0 0 18 0 40
## rs12476415_G 0 18 0 0 0 18 18 0
## rs7430710_A 0 0 18 18 18 18 0 18
## rs11257386_A 18 0 18 18 0 0 18 37
## rs2149733_A 0 18 18 18 18 18 18 18
## rs2168477_A 0 18 18 18 18 18 18 18
## rs10412466_G 18 0 0 36 18 18 18 18
## rs694625_A 0 0 18 0 0 0 40 18
## rs11150589_A 0 18 18 18 0 0 18 0
## rs16825228_G 0 0 0 0 0 18 0 0
## rs12005670_A 0 0 18 0 0 18 18 18
## rs12598978_A 0 18 18 18 0 0 18 0
## rs10405944_G 18 18 0 0 0 18 18 18
## rs12629469_A 0 37 18 0 0 38 0 0
## rs10063667_A 0 18 0 0 18 18 18 0
## rs8093884_A 37 0 0 0 0 0 18 0
## rs10795908_G 18 18 37 18 0 0 0 18
## rs4821456_G 39 0 0 0 0 18 0 0
## rs13058433_G 18 0 18 0 0 18 18 18
## rs7807747_A 18 0 18 0 18 0 0 0
## rs12679812_A 0 18 0 18 0 0 18 0
## rs11981000_G 0 0 0 0 0 18 38 0
## rs10050725_G 0 0 0 0 0 18 0 0
## rs4716858_A 36 0 18 18 0 0 0 18
## rs7840855_G 0 18 18 0 0 0 0 18
## rs818441_A 0 0 18 0 0 0 0 18
## rs4282978_A 0 0 38 37 18 0 37 0
## rs635070_A 0 18 36 0 0 0 0 0
## rs12794303_G 0 0 0 0 0 0 0 0
## rs9291002_A 0 40 0 18 0 0 18 18
## rs4932545_G 18 0 18 18 0 18 18 18
## rs742502_G 18 0 0 0 0 18 18 18
## rs1016090_G 0 18 18 18 0 0 0 0
## rs1732581_A 0 0 18 0 0 0 0 0
## rs750064_G 0 0 0 0 39 0 0 0
## rs4961252_G 0 0 0 0 18 0 0 0
## rs933881_G 0 0 0 0 36 0 0 0
## rs7327037_G 0 0 0 0 0 0 0 0
## rs1882153_A 0 0 18 0 0 0 0 0
## rs2835695_G 0 18 0 0 0 0 0 0
## rs11218557_G 0 0 0 0 0 0 18 0
## rs3095301_G 0 0 0 0 18 0 0 0
## rs3095302_A 0 0 0 0 18 0 0 0
## rs3131003_A 0 0 0 0 18 0 0 0
## rs7725574_C 0 0 0 0 0 0 0 0
## rs7912364_C 0 0 0 0 0 0 0 0
## iter35 iter36 iter37 iter38 iter39 iter40 iter41 iter42
## rs13279576_A 38 0.0 18 39 18 38 40 18
## rs7931183_A 39 35.0 0 18 0 39 18 0
## rs10837562_G 40 0.0 0 38 0 18 18 40
## rs9296990_A 0 17.5 0 18 0 18 37 39
## rs2331992_G 18 17.5 18 0 0 0 18 38
## rs12476415_G 18 0.0 18 36 40 18 18 18
## rs7430710_A 18 17.5 18 18 18 18 18 18
## rs11257386_A 0 17.5 37 0 0 0 0 18
## rs2149733_A 0 17.5 0 18 18 0 18 0
## rs2168477_A 18 17.5 0 18 0 0 18 0
## rs10412466_G 0 0.0 40 0 0 36 0 18
## rs694625_A 0 17.5 18 0 18 18 18 18
## rs11150589_A 0 0.0 18 0 18 18 18 18
## rs16825228_G 0 0.0 0 18 18 18 0 18
## rs12005670_A 0 17.5 0 18 0 0 0 18
## rs12598978_A 0 0.0 18 0 18 18 18 18
## rs10405944_G 18 17.5 18 18 0 0 0 18
## rs12629469_A 0 0.0 0 0 18 0 38 0
## rs10063667_A 0 17.5 18 18 18 18 18 0
## rs8093884_A 0 0.0 0 37 0 18 0 0
## rs10795908_G 0 0.0 18 0 0 0 39 18
## rs4821456_G 37 17.5 0 18 18 0 18 0
## rs13058433_G 0 0.0 18 0 0 0 0 0
## rs7807747_A 18 17.5 0 0 18 0 18 0
## rs12679812_A 18 0.0 18 18 0 0 18 18
## rs11981000_G 0 0.0 0 0 0 0 0 0
## rs10050725_G 18 0.0 0 0 0 37 0 0
## rs4716858_A 18 39.0 0 0 0 0 0 0
## rs7840855_G 0 17.5 0 18 0 0 0 18
## rs818441_A 0 17.5 18 0 0 18 0 18
## rs4282978_A 0 0.0 0 0 0 0 0 18
## rs635070_A 0 17.5 0 0 0 0 18 0
## rs12794303_G 0 0.0 18 18 0 18 18 18
## rs9291002_A 0 0.0 39 0 0 0 18 18
## rs4932545_G 0 0.0 0 0 18 0 18 0
## rs742502_G 0 0.0 18 0 0 0 0 0
## rs1016090_G 18 0.0 0 0 0 18 18 0
## rs1732581_A 0 0.0 0 0 18 0 0 0
## rs750064_G 0 0.0 38 18 0 0 0 0
## rs4961252_G 0 0.0 0 0 0 0 0 0
## rs933881_G 18 0.0 18 0 18 0 0 0
## rs7327037_G 0 36.0 18 0 18 0 0 0
## rs1882153_A 0 0.0 0 0 18 0 0 0
## rs2835695_G 0 0.0 0 0 0 0 0 0
## rs11218557_G 0 0.0 0 0 0 18 0 0
## rs3095301_G 0 0.0 0 0 0 0 0 0
## rs3095302_A 0 0.0 0 0 0 0 0 0
## rs3131003_A 0 0.0 0 0 0 0 0 0
## rs7725574_C 0 17.5 0 0 0 0 18 0
## rs7912364_C 18 0.0 0 18 0 0 18 0
## iter43 iter44 iter45 iter46 iter47 iter48 iter49 iter50
## rs13279576_A 18 40 39.0 39 18 0.0 18 38
## rs7931183_A 40 0 38.0 18 39 40.0 0 37
## rs10837562_G 18 0 35.0 40 0 0.0 0 0
## rs9296990_A 0 0 0.0 18 40 0.0 18 0
## rs2331992_G 18 0 0.0 18 18 39.0 40 0
## rs12476415_G 0 18 17.5 36 18 0.0 0 0
## rs7430710_A 0 0 17.5 18 18 17.5 18 18
## rs11257386_A 18 0 0.0 0 18 37.0 18 0
## rs2149733_A 18 18 17.5 18 18 17.5 0 18
## rs2168477_A 18 18 0.0 18 18 17.5 18 0
## rs10412466_G 37 0 17.5 0 0 0.0 0 0
## rs694625_A 0 0 17.5 18 18 0.0 0 0
## rs11150589_A 18 0 0.0 0 18 0.0 18 0
## rs16825228_G 0 0 17.5 18 0 0.0 0 0
## rs12005670_A 0 18 0.0 18 0 17.5 18 0
## rs12598978_A 18 0 0.0 0 18 0.0 18 0
## rs10405944_G 18 0 0.0 0 18 17.5 18 0
## rs12629469_A 0 0 0.0 18 0 0.0 18 18
## rs10063667_A 0 0 17.5 0 0 0.0 0 0
## rs8093884_A 0 39 0.0 0 18 17.5 37 0
## rs10795908_G 0 0 0.0 0 18 17.5 0 18
## rs4821456_G 0 0 0.0 18 37 17.5 18 0
## rs13058433_G 18 0 17.5 0 0 17.5 18 18
## rs7807747_A 0 18 17.5 18 0 0.0 0 0
## rs12679812_A 18 0 17.5 0 0 0.0 18 0
## rs11981000_G 0 18 17.5 0 0 0.0 0 0
## rs10050725_G 0 0 37.0 0 0 0.0 0 0
## rs4716858_A 18 0 0.0 0 36 17.5 0 0
## rs7840855_G 0 0 0.0 0 0 17.5 18 0
## rs818441_A 0 0 0.0 0 0 0.0 18 0
## rs4282978_A 18 0 0.0 18 0 0.0 0 0
## rs635070_A 0 0 17.5 0 0 0.0 0 0
## rs12794303_G 0 0 0.0 18 0 17.5 0 0
## rs9291002_A 18 0 0.0 0 0 0.0 0 0
## rs4932545_G 0 0 0.0 18 18 0.0 0 0
## rs742502_G 0 0 0.0 0 0 17.5 18 18
## rs1016090_G 0 0 0.0 18 18 0.0 0 0
## rs1732581_A 0 0 17.5 18 18 17.5 18 0
## rs750064_G 18 0 0.0 0 0 0.0 36 0
## rs4961252_G 0 0 0.0 0 0 0.0 0 18
## rs933881_G 0 0 36.0 0 0 0.0 0 39
## rs7327037_G 39 0 0.0 0 0 0.0 0 18
## rs1882153_A 0 0 17.5 18 18 17.5 18 0
## rs2835695_G 18 0 17.5 0 0 0.0 0 0
## rs11218557_G 0 0 0.0 0 0 17.5 0 0
## rs3095301_G 0 37 17.5 0 0 17.5 0 0
## rs3095302_A 0 37 17.5 0 0 17.5 0 0
## rs3131003_A 0 37 17.5 0 0 17.5 0 0
## rs7725574_C 0 0 0.0 0 18 0.0 0 0
## rs7912364_C 0 0 0.0 18 0 0.0 0 0
## iter51 iter52 iter53 iter54 iter55 iter56 iter57 iter58
## rs13279576_A 0 0 38 0 40.0 37 0 38
## rs7931183_A 18 0 18 0 39.0 18 39 18
## rs10837562_G 36 0 0 40 17.5 18 40 40
## rs9296990_A 0 0 18 36 0.0 0 18 18
## rs2331992_G 18 0 37 38 0.0 0 0 37
## rs12476415_G 18 17 18 18 35.5 0 0 18
## rs7430710_A 0 0 0 18 17.5 0 0 18
## rs11257386_A 40 0 18 39 17.5 0 0 18
## rs2149733_A 18 0 18 18 17.5 0 18 18
## rs2168477_A 18 17 18 18 17.5 0 0 18
## rs10412466_G 0 34 18 0 0.0 0 36 18
## rs694625_A 0 0 18 0 17.5 18 0 0
## rs11150589_A 18 0 18 0 0.0 18 18 18
## rs16825228_G 0 17 0 18 35.5 0 0 0
## rs12005670_A 0 0 0 0 0.0 0 18 0
## rs12598978_A 18 0 18 0 0.0 18 18 18
## rs10405944_G 18 0 0 0 0.0 0 18 18
## rs12629469_A 38 0 18 18 17.5 18 0 18
## rs10063667_A 18 17 18 18 17.5 0 0 18
## rs8093884_A 0 37 39 0 0.0 18 18 0
## rs10795908_G 37 0 18 37 0.0 0 0 0
## rs4821456_G 18 0 0 18 17.5 0 0 0
## rs13058433_G 0 0 0 0 17.5 40 0 0
## rs7807747_A 18 0 0 18 17.5 0 0 36
## rs12679812_A 18 0 0 0 17.5 18 0 0
## rs11981000_G 18 0 0 0 17.5 0 18 18
## rs10050725_G 0 0 0 18 0.0 0 37 39
## rs4716858_A 18 0 0 0 0.0 38 0 18
## rs7840855_G 18 17 0 18 0.0 0 0 18
## rs818441_A 18 0 0 0 0.0 0 18 0
## rs4282978_A 0 0 0 18 0.0 0 0 0
## rs635070_A 18 0 18 18 38.0 18 0 18
## rs12794303_G 0 0 18 0 0.0 0 0 0
## rs9291002_A 18 0 0 0 0.0 0 0 0
## rs4932545_G 0 17 0 18 0.0 0 0 0
## rs742502_G 0 0 0 0 0.0 39 0 0
## rs1016090_G 18 0 0 18 0.0 18 0 0
## rs1732581_A 0 0 18 0 0.0 0 0 0
## rs750064_G 0 0 36 0 0.0 0 0 0
## rs4961252_G 0 0 18 0 17.5 0 0 0
## rs933881_G 0 17 0 0 0.0 0 0 18
## rs7327037_G 0 36 0 0 0.0 0 0 0
## rs1882153_A 0 0 18 0 0.0 0 0 0
## rs2835695_G 18 0 0 0 0.0 0 0 0
## rs11218557_G 0 17 0 0 0.0 0 38 0
## rs3095301_G 0 0 0 0 0.0 0 0 0
## rs3095302_A 0 0 0 0 0.0 0 0 0
## rs3131003_A 0 0 0 0 0.0 0 0 0
## rs7725574_C 0 0 0 0 37.0 0 0 0
## rs7912364_C 0 0 0 18 0.0 0 0 0
## iter59 iter60 iter61 iter62 iter63 iter64 iter65 iter66
## rs13279576_A 18 38 40 37 0 0 40 39.0
## rs7931183_A 0 40 39 0 18 18 38 17.5
## rs10837562_G 38 18 0 0 40 0 37 35.0
## rs9296990_A 18 18 38 18 0 0 18 17.5
## rs2331992_G 18 39 0 18 38 0 39 38.0
## rs12476415_G 18 18 37 18 18 0 18 17.5
## rs7430710_A 0 18 0 18 18 18 0 0.0
## rs11257386_A 36 37 18 18 0 18 36 17.5
## rs2149733_A 0 18 18 18 18 18 0 0.0
## rs2168477_A 0 18 18 18 18 18 18 17.5
## rs10412466_G 0 18 18 0 0 0 18 0.0
## rs694625_A 39 0 0 0 0 18 18 0.0
## rs11150589_A 18 0 18 0 18 0 18 17.5
## rs16825228_G 18 18 18 18 0 0 18 0.0
## rs12005670_A 0 0 0 18 18 0 18 17.5
## rs12598978_A 18 0 18 0 18 0 18 17.5
## rs10405944_G 0 18 0 18 18 0 0 17.5
## rs12629469_A 0 18 0 0 0 0 0 17.5
## rs10063667_A 0 18 0 0 0 18 0 0.0
## rs8093884_A 0 18 0 0 36 0 18 0.0
## rs10795908_G 37 18 0 0 0 18 18 0.0
## rs4821456_G 0 0 0 0 37 18 18 37.0
## rs13058433_G 0 0 0 0 0 0 0 0.0
## rs7807747_A 0 0 0 18 0 18 0 0.0
## rs12679812_A 0 0 0 0 18 0 0 0.0
## rs11981000_G 0 0 18 0 0 0 0 0.0
## rs10050725_G 0 0 0 0 18 0 18 17.5
## rs4716858_A 0 0 0 0 0 0 0 0.0
## rs7840855_G 18 0 0 0 0 0 18 0.0
## rs818441_A 0 0 0 18 18 0 18 0.0
## rs4282978_A 18 18 0 0 0 0 0 0.0
## rs635070_A 0 0 0 0 18 18 0 0.0
## rs12794303_G 0 0 0 0 0 0 0 17.5
## rs9291002_A 0 18 0 0 0 0 0 17.5
## rs4932545_G 0 0 0 18 0 0 18 0.0
## rs742502_G 0 0 0 0 0 0 0 0.0
## rs1016090_G 0 0 0 0 0 18 0 0.0
## rs1732581_A 18 0 0 18 0 0 0 0.0
## rs750064_G 40 0 0 0 18 0 0 0.0
## rs4961252_G 18 0 0 39 0 38 0 0.0
## rs933881_G 0 0 0 0 0 0 0 0.0
## rs7327037_G 0 18 0 0 0 36 0 0.0
## rs1882153_A 0 0 0 18 0 0 0 0.0
## rs2835695_G 0 0 18 0 0 0 0 0.0
## rs11218557_G 0 18 18 0 0 0 0 0.0
## rs3095301_G 0 0 18 0 0 0 0 0.0
## rs3095302_A 0 0 18 0 0 0 0 0.0
## rs3131003_A 0 0 18 0 0 0 0 0.0
## rs7725574_C 0 18 0 0 18 0 18 0.0
## rs7912364_C 0 0 0 18 0 0 0 17.5
## iter67 iter68 iter69 iter70 iter71 iter72 iter73 iter74
## rs13279576_A 39 18 40.0 36 18 18 0 0
## rs7931183_A 18 18 18.0 0 38 0 0 18
## rs10837562_G 18 18 18.0 40 0 38 40 0
## rs9296990_A 18 37 0.0 18 0 18 18 0
## rs2331992_G 0 40 18.0 18 36 18 0 0
## rs12476415_G 0 18 37.5 18 37 0 18 18
## rs7430710_A 18 18 18.0 18 0 18 18 0
## rs11257386_A 0 0 18.0 18 0 39 0 18
## rs2149733_A 0 18 18.0 18 18 18 0 0
## rs2168477_A 0 18 18.0 18 18 18 0 18
## rs10412466_G 18 18 18.0 0 39 0 0 0
## rs694625_A 0 18 36.0 39 40 37 18 0
## rs11150589_A 18 18 0.0 0 0 0 0 0
## rs16825228_G 0 18 37.5 18 18 0 0 0
## rs12005670_A 18 18 18.0 18 0 18 0 0
## rs12598978_A 18 18 0.0 0 0 0 0 0
## rs10405944_G 0 18 0.0 0 18 0 18 0
## rs12629469_A 18 0 18.0 0 0 0 0 18
## rs10063667_A 18 18 18.0 0 18 18 0 0
## rs8093884_A 18 18 0.0 0 18 18 37 0
## rs10795908_G 0 0 18.0 0 0 36 39 0
## rs4821456_G 0 0 0.0 18 18 18 0 18
## rs13058433_G 18 18 0.0 0 0 0 0 0
## rs7807747_A 18 18 0.0 18 18 18 0 18
## rs12679812_A 18 0 0.0 0 18 18 0 0
## rs11981000_G 0 0 18.0 0 0 0 0 0
## rs10050725_G 38 0 0.0 0 0 18 0 18
## rs4716858_A 18 18 0.0 0 0 0 0 0
## rs7840855_G 0 0 18.0 0 0 0 18 0
## rs818441_A 0 18 0.0 18 0 0 0 18
## rs4282978_A 0 0 0.0 0 0 0 38 18
## rs635070_A 0 0 0.0 0 18 0 0 0
## rs12794303_G 18 0 18.0 18 0 18 0 18
## rs9291002_A 18 0 0.0 18 0 0 0 18
## rs4932545_G 0 0 0.0 0 0 0 18 18
## rs742502_G 18 18 0.0 0 0 0 0 0
## rs1016090_G 0 0 0.0 0 0 18 18 0
## rs1732581_A 0 18 18.0 0 18 0 0 0
## rs750064_G 0 38 39.0 0 0 0 0 0
## rs4961252_G 0 0 18.0 0 0 0 0 18
## rs933881_G 40 0 0.0 0 0 0 0 18
## rs7327037_G 18 0 0.0 0 0 0 0 0
## rs1882153_A 0 18 18.0 0 18 0 0 0
## rs2835695_G 0 0 0.0 0 0 18 0 39
## rs11218557_G 0 0 0.0 0 18 0 0 0
## rs3095301_G 0 0 0.0 18 0 18 0 0
## rs3095302_A 0 0 0.0 18 0 18 0 0
## rs3131003_A 0 0 0.0 18 0 18 0 0
## rs7725574_C 0 0 0.0 0 18 0 0 18
## rs7912364_C 18 18 0.0 0 0 0 0 0
## iter75 iter76 iter77 iter78 iter79 iter80 iter81 iter82
## rs13279576_A 40 18 18 18 18 18 37 0
## rs7931183_A 37 37 18 0 36 18 40 0
## rs10837562_G 18 40 0 0 40 18 0 0
## rs9296990_A 39 0 0 18 18 18 0 0
## rs2331992_G 18 36 40 0 18 0 18 39
## rs12476415_G 18 18 18 18 0 36 18 18
## rs7430710_A 0 0 18 0 18 18 18 18
## rs11257386_A 0 39 18 0 0 0 0 18
## rs2149733_A 0 0 18 18 0 18 18 18
## rs2168477_A 18 0 18 18 0 18 18 18
## rs10412466_G 0 0 36 39 38 18 18 0
## rs694625_A 0 18 0 0 18 18 18 0
## rs11150589_A 0 0 18 18 18 0 0 0
## rs16825228_G 18 18 18 18 0 18 18 18
## rs12005670_A 18 0 18 0 0 0 0 18
## rs12598978_A 0 0 18 18 18 0 0 0
## rs10405944_G 18 0 18 0 18 18 0 18
## rs12629469_A 38 18 0 0 0 0 0 18
## rs10063667_A 0 0 0 0 0 18 18 18
## rs8093884_A 18 0 0 0 0 0 0 0
## rs10795908_G 0 0 0 18 0 0 0 0
## rs4821456_G 0 0 0 36 0 0 0 18
## rs13058433_G 0 0 0 0 18 0 0 0
## rs7807747_A 0 18 0 0 0 0 0 40
## rs12679812_A 0 0 18 0 18 0 0 18
## rs11981000_G 0 0 0 0 0 40 0 0
## rs10050725_G 0 0 0 0 0 18 0 0
## rs4716858_A 0 18 0 0 0 0 0 0
## rs7840855_G 0 0 0 0 0 18 0 0
## rs818441_A 18 0 0 0 0 0 0 0
## rs4282978_A 0 0 18 40 0 0 36 0
## rs635070_A 0 18 0 0 0 0 38 0
## rs12794303_G 0 0 0 0 0 18 18 0
## rs9291002_A 0 0 38 0 39 0 18 0
## rs4932545_G 18 0 0 0 0 0 0 18
## rs742502_G 0 0 0 0 18 0 0 0
## rs1016090_G 0 0 0 18 0 18 0 0
## rs1732581_A 0 18 18 0 18 0 18 0
## rs750064_G 0 0 18 0 0 0 0 0
## rs4961252_G 0 18 0 0 0 0 39 0
## rs933881_G 0 18 0 0 18 0 18 0
## rs7327037_G 0 0 39 0 18 0 18 0
## rs1882153_A 0 18 18 0 18 0 18 0
## rs2835695_G 0 0 0 18 0 18 18 38
## rs11218557_G 18 0 0 0 0 0 0 0
## rs3095301_G 18 0 0 18 0 38 0 18
## rs3095302_A 18 0 0 18 0 38 0 18
## rs3131003_A 18 0 0 18 0 38 0 18
## rs7725574_C 0 18 0 0 0 0 0 0
## rs7912364_C 18 0 0 0 0 0 18 0
## iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90
## rs13279576_A 18 0 0 37 17.5 38 18 40
## rs7931183_A 39 38 37 36 37.0 40 40 17
## rs10837562_G 40 18 0 40 38.0 39 37 17
## rs9296990_A 37 36 18 18 0.0 18 18 39
## rs2331992_G 36 40 18 39 17.5 18 38 0
## rs12476415_G 0 0 0 18 0.0 18 0 17
## rs7430710_A 18 0 18 18 0.0 18 18 17
## rs11257386_A 0 18 36 0 0.0 37 36 17
## rs2149733_A 0 0 18 18 17.5 0 18 17
## rs2168477_A 18 18 18 0 0.0 18 0 17
## rs10412466_G 18 39 0 18 39.0 0 18 0
## rs694625_A 0 0 0 18 0.0 18 0 0
## rs11150589_A 18 18 0 18 0.0 18 18 17
## rs16825228_G 0 0 0 18 0.0 18 0 0
## rs12005670_A 18 18 18 18 0.0 0 0 0
## rs12598978_A 18 18 0 18 0.0 18 18 17
## rs10405944_G 18 18 0 18 17.5 0 0 0
## rs12629469_A 0 18 18 0 0.0 18 0 17
## rs10063667_A 0 0 0 0 17.5 18 0 17
## rs8093884_A 0 0 0 0 36.0 18 0 0
## rs10795908_G 0 0 38 0 0.0 18 0 0
## rs4821456_G 0 0 18 0 0.0 0 0 0
## rs13058433_G 18 18 18 18 0.0 0 0 0
## rs7807747_A 0 0 0 0 0.0 0 0 0
## rs12679812_A 18 18 0 18 17.5 0 0 0
## rs11981000_G 18 18 0 0 0.0 0 0 0
## rs10050725_G 0 0 0 0 0.0 0 18 38
## rs4716858_A 0 0 40 0 0.0 0 18 0
## rs7840855_G 18 0 18 0 17.5 0 0 17
## rs818441_A 18 18 0 0 17.5 0 0 0
## rs4282978_A 0 0 0 0 0.0 0 0 0
## rs635070_A 18 0 0 0 0.0 18 0 0
## rs12794303_G 18 0 0 0 17.5 0 0 0
## rs9291002_A 0 0 39 18 0.0 0 0 0
## rs4932545_G 0 0 18 0 0.0 0 18 17
## rs742502_G 0 18 18 0 0.0 0 0 0
## rs1016090_G 0 0 18 0 17.5 0 18 17
## rs1732581_A 0 0 18 0 0.0 0 18 17
## rs750064_G 0 0 0 0 17.5 0 0 0
## rs4961252_G 0 0 0 0 0.0 0 0 0
## rs933881_G 0 0 0 0 0.0 36 0 0
## rs7327037_G 0 0 0 0 0.0 0 0 0
## rs1882153_A 0 0 18 0 0.0 0 18 0
## rs2835695_G 0 0 0 0 0.0 0 0 0
## rs11218557_G 0 0 0 0 17.5 0 39 0
## rs3095301_G 0 18 0 0 17.5 0 0 35
## rs3095302_A 0 18 0 0 17.5 0 0 35
## rs3131003_A 0 18 0 0 17.5 0 0 35
## rs7725574_C 18 0 18 18 17.5 0 0 0
## rs7912364_C 0 18 0 18 0.0 0 0 0
## iter91 iter92 iter93 iter94 iter95 iter96 iter97 iter98
## rs13279576_A 40 37.0 0 18 37 18 36 40
## rs7931183_A 0 40.0 18 0 38 0 37 18
## rs10837562_G 18 0.0 0 38 0 40 39 18
## rs9296990_A 18 18.0 36 18 0 18 38 18
## rs2331992_G 0 18.0 0 0 0 18 0 18
## rs12476415_G 38 38.5 0 18 18 0 18 18
## rs7430710_A 18 18.0 18 0 18 0 18 0
## rs11257386_A 0 0.0 0 0 0 36 0 0
## rs2149733_A 18 18.0 18 18 18 0 0 18
## rs2168477_A 18 18.0 0 18 18 0 0 18
## rs10412466_G 18 0.0 18 39 0 0 0 39
## rs694625_A 18 18.0 18 0 0 0 40 0
## rs11150589_A 18 0.0 18 0 0 0 18 0
## rs16825228_G 18 38.5 0 18 0 0 18 18
## rs12005670_A 18 0.0 0 18 18 18 0 18
## rs12598978_A 18 0.0 18 0 0 0 18 0
## rs10405944_G 0 0.0 0 18 0 18 18 0
## rs12629469_A 18 18.0 0 0 0 38 0 37
## rs10063667_A 0 18.0 0 18 18 0 18 0
## rs8093884_A 0 0.0 0 18 0 0 18 0
## rs10795908_G 0 0.0 0 0 0 39 0 0
## rs4821456_G 0 18.0 0 18 0 18 0 38
## rs13058433_G 36 0.0 37 0 18 18 0 0
## rs7807747_A 0 0.0 18 0 0 0 0 0
## rs12679812_A 0 18.0 0 18 0 0 18 18
## rs11981000_G 18 18.0 0 18 0 18 18 0
## rs10050725_G 0 0.0 0 0 0 0 0 0
## rs4716858_A 0 0.0 0 0 0 18 0 0
## rs7840855_G 0 0.0 0 0 0 18 0 18
## rs818441_A 18 0.0 0 0 18 0 0 18
## rs4282978_A 0 0.0 0 36 18 0 0 0
## rs635070_A 0 0.0 0 18 39 0 0 0
## rs12794303_G 0 0.0 18 0 0 18 18 0
## rs9291002_A 0 18.0 0 0 0 0 0 0
## rs4932545_G 0 0.0 18 0 0 0 0 0
## rs742502_G 18 0.0 18 0 18 18 0 0
## rs1016090_G 18 0.0 0 18 0 0 0 18
## rs1732581_A 0 0.0 0 0 0 0 0 0
## rs750064_G 0 0.0 18 0 0 0 18 0
## rs4961252_G 0 0.0 18 0 40 0 0 0
## rs933881_G 0 0.0 0 0 0 0 0 0
## rs7327037_G 0 0.0 0 0 0 0 0 0
## rs1882153_A 0 0.0 0 0 0 0 0 0
## rs2835695_G 0 0.0 18 18 18 0 0 18
## rs11218557_G 0 0.0 0 0 18 0 18 36
## rs3095301_G 0 0.0 0 18 0 0 0 0
## rs3095302_A 0 0.0 0 18 0 0 0 0
## rs3131003_A 0 0.0 0 18 0 0 0 0
## rs7725574_C 0 18.0 0 0 0 18 0 0
## rs7912364_C 18 18.0 0 0 0 0 0 18
## iter99 iter100 total_rank
## rs13279576_A 40 0 2408.0
## rs7931183_A 18 40 2331.5
## rs10837562_G 0 0 2009.5
## rs9296990_A 0 0 1497.5
## rs2331992_G 0 0 1443.0
## rs12476415_G 18 0 1435.0
## rs7430710_A 18 0 1274.0
## rs11257386_A 0 0 1231.5
## rs2149733_A 18 18 1220.0
## rs2168477_A 18 18 1201.0
## rs10412466_G 0 0 1179.5
## rs694625_A 0 0 1050.0
## rs11150589_A 0 18 898.0
## rs16825228_G 18 0 886.5
## rs12005670_A 18 18 880.5
## rs12598978_A 0 18 880.0
## rs10405944_G 0 0 879.0
## rs12629469_A 0 0 862.0
## rs10063667_A 0 0 859.5
## rs8093884_A 0 0 857.5
## rs10795908_G 0 0 810.5
## rs4821456_G 0 18 763.5
## rs13058433_G 0 18 729.0
## rs7807747_A 0 0 650.5
## rs12679812_A 0 0 646.5
## rs11981000_G 18 0 630.0
## rs10050725_G 0 0 625.5
## rs4716858_A 0 18 612.5
## rs7840855_G 18 18 607.5
## rs818441_A 0 0 592.0
## rs4282978_A 0 0 589.5
## rs635070_A 0 18 582.0
## rs12794303_G 0 0 574.0
## rs9291002_A 0 18 572.0
## rs4932545_G 0 18 538.0
## rs742502_G 18 18 528.0
## rs1016090_G 0 0 484.5
## rs1732581_A 18 0 483.5
## rs750064_G 0 0 481.0
## rs4961252_G 0 0 461.0
## rs933881_G 0 0 441.5
## rs7327037_G 0 38 440.0
## rs1882153_A 18 0 430.5
## rs2835695_G 0 0 420.5
## rs11218557_G 0 0 416.5
## rs3095301_G 0 0 414.5
## rs3095302_A 0 0 414.5
## rs3131003_A 0 0 414.5
## rs7725574_C 0 36 414.0
## rs7912364_C 0 0 412.5write.table(gen_features_comp1_final,file="Comp1_GEN_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
gen_features_comp2_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),gen_features_comp2)
rownames(gen_features_comp2_final)<-gen_features_comp2_final$GENE
gen_features_comp2_final$GENE<-NULL
gen_features_comp2_final[is.na(gen_features_comp2_final)]<-0
gen_features_comp2_final$total_rank<-rowSums(gen_features_comp2_final)
gen_features_comp2_final<-gen_features_comp2_final[order(-gen_features_comp2_final$total_rank),]
print(head(gen_features_comp2_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10
## rs12476415_G 18 18 18 0 38 0.0 0 18 0 18
## rs7931183_A 0 18 0 18 18 17.5 18 18 18 0
## rs9296990_A 18 0 0 37 40 39.0 18 0 39 18
## rs13279576_A 18 0 18 18 18 17.5 0 18 18 18
## rs7430710_A 18 0 18 18 0 17.5 18 0 18 18
## rs2149733_A 18 0 0 18 0 17.5 0 18 0 18
## rs694625_A 0 38 18 38 18 0.0 0 0 0 36
## rs2168477_A 18 0 18 18 0 17.5 0 18 0 0
## rs10837562_G 18 18 0 18 18 17.5 18 18 18 18
## rs7807747_A 0 0 0 39 0 0.0 39 40 0 38
## rs10405944_G 0 0 18 0 18 38.0 0 0 18 18
## rs2331992_G 18 0 0 0 0 0.0 18 0 18 18
## rs8093884_A 39 40 0 18 18 0.0 37 0 0 0
## rs10412466_G 18 0 18 0 0 17.5 0 36 0 18
## rs16825228_G 0 0 18 0 37 0.0 0 0 0 18
## rs10063667_A 0 18 0 0 18 36.0 18 18 0 0
## rs11150589_A 18 18 18 18 18 0.0 18 0 0 0
## rs12005670_A 18 18 0 18 0 0.0 0 18 18 0
## rs11257386_A 18 0 0 18 18 0.0 18 0 0 0
## rs12598978_A 18 18 18 18 0 0.0 18 0 0 0
## rs4821456_G 38 0 0 0 0 0.0 0 0 0 18
## rs635070_A 0 0 0 0 0 0.0 40 0 18 0
## rs12629469_A 0 0 18 18 18 0.0 0 18 0 0
## rs13058433_G 0 36 0 0 0 0.0 0 0 18 0
## rs11981000_G 0 0 0 0 36 0.0 18 18 38 0
## rs10050725_G 0 0 0 0 0 17.5 0 18 0 18
## rs12679812_A 0 0 0 0 0 0.0 0 18 18 0
## rs12794303_G 0 0 0 0 0 17.5 0 0 0 18
## rs7840855_G 18 0 18 0 0 17.5 18 0 18 0
## rs10795908_G 0 18 0 0 0 0.0 18 0 0 0
## rs818441_A 18 0 18 18 0 17.5 0 0 18 0
## rs2835695_G 0 0 0 0 0 0.0 36 0 0 0
## rs4932545_G 0 0 0 18 0 0.0 18 18 0 0
## rs11218557_G 18 0 37 40 0 0.0 0 0 0 0
## rs9291002_A 0 0 0 0 0 17.5 18 0 0 0
## rs742502_G 0 18 0 0 0 0.0 0 0 18 0
## rs1732581_A 18 0 18 0 0 0.0 0 0 0 0
## rs1016090_G 0 0 0 0 0 0.0 0 0 0 0
## rs327826_G 40 0 40 18 18 17.5 0 0 0 0
## rs4716858_A 0 18 0 0 0 0.0 0 0 18 18
## rs4961252_G 0 0 0 0 39 35.0 0 0 0 0
## rs1882153_A 18 0 18 0 0 0.0 0 0 0 0
## rs10217194_A 0 37 0 0 0 0.0 0 39 0 0
## rs4282978_A 0 0 18 0 0 0.0 0 18 0 0
## rs7912364_C 0 0 18 18 0 17.5 0 0 0 18
## rs2212736_G 0 0 0 0 0 0.0 18 0 0 0
## rs1552046_G 0 0 0 0 0 0.0 0 18 18 0
## rs3095301_G 0 18 0 0 0 0.0 18 0 0 0
## rs3095302_A 0 18 0 0 0 0.0 18 0 0 0
## rs3131003_A 0 18 0 0 0 0.0 18 0 0 0
## iter11 iter12 iter13 iter14 iter15 iter16 iter17 iter18
## rs12476415_G 38 18 0 18 0 0 18 0
## rs7931183_A 18 0 18 18 40 18 18 0
## rs9296990_A 0 18 18 18 0 18 18 37
## rs13279576_A 18 18 18 18 18 18 18 18
## rs7430710_A 18 18 18 18 18 18 18 18
## rs2149733_A 18 0 18 0 18 18 18 18
## rs694625_A 0 37 0 0 0 0 37 0
## rs2168477_A 18 18 0 18 18 0 0 0
## rs10837562_G 18 18 18 0 0 18 18 18
## rs7807747_A 0 0 0 0 0 0 38 0
## rs10405944_G 18 0 0 0 0 18 0 39
## rs2331992_G 0 18 0 18 0 0 0 0
## rs8093884_A 0 40 0 18 0 18 0 0
## rs10412466_G 0 0 18 0 0 0 0 18
## rs16825228_G 0 18 0 18 0 0 18 0
## rs10063667_A 18 0 18 0 18 18 18 18
## rs11150589_A 18 0 18 0 0 18 18 0
## rs12005670_A 18 18 0 18 0 18 18 0
## rs11257386_A 0 0 0 0 0 0 18 0
## rs12598978_A 18 0 18 0 0 18 18 0
## rs4821456_G 0 0 0 0 0 0 18 0
## rs635070_A 0 0 0 39 0 0 0 0
## rs12629469_A 18 18 0 0 0 0 0 0
## rs13058433_G 18 0 0 18 0 0 18 18
## rs11981000_G 0 0 0 0 18 18 18 0
## rs10050725_G 40 0 18 0 0 37 39 38
## rs12679812_A 18 0 0 18 0 0 18 0
## rs12794303_G 18 18 0 18 0 0 18 0
## rs7840855_G 0 0 0 0 0 18 0 18
## rs10795908_G 0 0 0 0 0 0 18 0
## rs818441_A 18 0 0 18 0 0 18 0
## rs2835695_G 0 0 36 0 39 39 0 0
## rs4932545_G 0 0 0 0 0 18 18 0
## rs11218557_G 0 0 0 0 36 0 0 0
## rs9291002_A 0 0 0 0 0 0 18 0
## rs742502_G 0 0 0 18 0 0 0 18
## rs1732581_A 0 0 0 0 0 18 0 0
## rs1016090_G 0 0 18 0 18 0 18 18
## rs327826_G 0 39 0 0 0 0 0 0
## rs4716858_A 0 0 0 0 0 0 18 0
## rs4961252_G 0 0 0 37 18 0 0 0
## rs1882153_A 0 0 0 0 0 18 0 0
## rs10217194_A 0 0 0 0 0 0 0 0
## rs4282978_A 0 0 0 0 0 0 18 18
## rs7912364_C 0 0 0 0 0 18 0 18
## rs2212736_G 0 0 37 0 37 40 0 0
## rs1552046_G 18 0 0 18 0 0 18 36
## rs3095301_G 0 18 0 0 0 0 0 0
## rs3095302_A 0 18 0 0 0 0 0 0
## rs3131003_A 0 18 0 0 0 0 0 0
## iter19 iter20 iter21 iter22 iter23 iter24 iter25 iter26
## rs12476415_G 0 18 18 0 36 18 37 0
## rs7931183_A 18 18 18 18 18 37 18 18
## rs9296990_A 18 0 0 37 0 0 36 0
## rs13279576_A 18 18 18 18 18 18 0 0
## rs7430710_A 18 18 18 0 18 18 18 18
## rs2149733_A 18 18 18 0 0 18 18 0
## rs694625_A 0 18 39 38 18 18 0 0
## rs2168477_A 0 0 18 18 0 18 18 0
## rs10837562_G 18 18 0 0 0 0 18 0
## rs7807747_A 0 36 18 39 0 0 0 18
## rs10405944_G 18 0 0 18 0 18 38 36
## rs2331992_G 18 0 18 18 0 0 0 0
## rs8093884_A 0 0 0 18 18 0 40 18
## rs10412466_G 0 18 0 0 18 0 0 0
## rs16825228_G 0 18 18 0 0 18 18 0
## rs10063667_A 18 18 0 0 0 0 18 0
## rs11150589_A 18 0 18 18 0 0 0 0
## rs12005670_A 0 0 18 18 18 0 18 0
## rs11257386_A 18 18 18 18 18 18 0 0
## rs12598978_A 18 0 18 18 0 0 0 0
## rs4821456_G 0 18 0 0 0 0 0 0
## rs635070_A 0 0 0 18 0 18 39 18
## rs12629469_A 18 0 0 0 0 0 0 0
## rs13058433_G 0 18 0 18 0 0 0 18
## rs11981000_G 0 37 0 0 18 0 0 0
## rs10050725_G 39 0 0 0 37 0 0 0
## rs12679812_A 18 0 0 0 0 0 18 0
## rs12794303_G 37 18 18 0 18 18 0 0
## rs7840855_G 0 0 0 0 0 0 18 18
## rs10795908_G 18 18 18 0 18 18 0 0
## rs818441_A 0 18 0 0 0 18 18 0
## rs2835695_G 0 0 0 18 0 0 0 0
## rs4932545_G 0 0 0 18 0 0 18 0
## rs11218557_G 0 39 18 0 0 0 0 0
## rs9291002_A 0 38 0 18 0 0 0 0
## rs742502_G 0 18 0 18 0 0 0 18
## rs1732581_A 0 18 18 0 0 18 0 0
## rs1016090_G 0 0 0 0 0 0 0 0
## rs327826_G 0 0 0 0 0 0 0 0
## rs4716858_A 18 18 0 0 0 0 0 0
## rs4961252_G 18 0 0 0 0 18 0 18
## rs1882153_A 0 18 18 0 0 0 0 0
## rs10217194_A 0 0 0 18 18 0 0 0
## rs4282978_A 0 18 18 0 0 0 0 0
## rs7912364_C 0 0 0 0 0 18 0 0
## rs2212736_G 0 0 0 0 0 0 0 0
## rs1552046_G 0 0 0 0 0 0 0 0
## rs3095301_G 0 0 0 0 18 0 0 18
## rs3095302_A 0 0 0 0 18 0 0 18
## rs3131003_A 0 0 0 0 18 0 0 18
## iter27 iter28 iter29 iter30 iter31 iter32 iter33 iter34
## rs12476415_G 0 17.5 0 0 0 18 18 0
## rs7931183_A 18 17.5 0 18 38 0 18 18
## rs9296990_A 0 0.0 36 18 37 18 0 38
## rs13279576_A 0 17.5 18 18 18 18 18 0
## rs7430710_A 0 0.0 18 18 18 18 0 18
## rs2149733_A 0 17.5 18 18 18 18 18 18
## rs694625_A 0 0.0 18 0 0 0 18 40
## rs2168477_A 0 17.5 18 18 18 18 18 18
## rs10837562_G 0 17.5 18 18 18 18 0 18
## rs7807747_A 18 0.0 37 0 18 0 0 0
## rs10405944_G 18 17.5 0 0 0 18 18 18
## rs2331992_G 18 0.0 0 0 0 40 0 18
## rs8093884_A 18 0.0 0 0 0 0 39 0
## rs10412466_G 36 0.0 0 18 18 38 18 39
## rs16825228_G 0 0.0 0 0 0 18 0 0
## rs10063667_A 0 17.5 0 0 39 18 18 0
## rs11150589_A 0 17.5 18 18 0 0 18 0
## rs12005670_A 0 0.0 18 0 0 18 18 18
## rs11257386_A 18 0.0 18 18 0 0 18 18
## rs12598978_A 0 17.5 18 18 0 0 18 0
## rs4821456_G 18 0.0 0 0 0 39 0 0
## rs635070_A 0 39.0 38 0 0 0 0 0
## rs12629469_A 0 17.5 18 0 0 18 0 0
## rs13058433_G 18 0.0 18 0 0 18 18 18
## rs11981000_G 0 0.0 0 0 0 37 18 0
## rs10050725_G 0 0.0 0 0 0 18 0 0
## rs12679812_A 0 17.5 0 18 0 0 18 0
## rs12794303_G 0 0.0 0 0 0 0 0 0
## rs7840855_G 0 17.5 18 0 0 0 0 18
## rs10795908_G 18 17.5 18 18 0 0 0 18
## rs818441_A 0 0.0 18 0 0 0 0 18
## rs2835695_G 0 38.0 0 0 0 0 0 0
## rs4932545_G 18 0.0 18 18 0 18 18 18
## rs11218557_G 0 0.0 0 0 0 0 38 0
## rs9291002_A 0 17.5 0 18 0 0 37 18
## rs742502_G 18 0.0 0 0 0 18 18 36
## rs1732581_A 0 0.0 18 0 0 0 0 0
## rs1016090_G 0 17.5 18 18 0 0 0 0
## rs327826_G 0 0.0 0 39 0 0 0 18
## rs4716858_A 18 0.0 18 18 0 0 0 18
## rs4961252_G 0 0.0 0 0 18 0 0 0
## rs1882153_A 0 0.0 18 0 0 0 0 0
## rs10217194_A 0 0.0 0 0 0 0 0 0
## rs4282978_A 0 0.0 18 18 18 0 18 0
## rs7912364_C 0 0.0 0 0 0 0 0 0
## rs2212736_G 0 0.0 0 0 0 0 0 0
## rs1552046_G 0 0.0 0 37 0 0 18 0
## rs3095301_G 0 0.0 0 0 18 0 0 0
## rs3095302_A 0 0.0 0 0 18 0 0 0
## rs3131003_A 0 0.0 0 0 18 0 0 0
## iter35 iter36 iter37 iter38 iter39 iter40 iter41 iter42
## rs12476415_G 18 0.0 36 18 18 36 18 37
## rs7931183_A 18 17.5 0 18 0 18 18 0
## rs9296990_A 0 17.5 0 18 0 40 36 18
## rs13279576_A 18 0.0 18 18 18 18 18 18
## rs7430710_A 18 17.5 18 18 18 18 18 18
## rs2149733_A 0 17.5 0 18 18 0 18 0
## rs694625_A 0 37.0 40 0 39 37 18 40
## rs2168477_A 18 17.5 0 18 0 0 18 0
## rs10837562_G 18 0.0 0 18 0 18 18 18
## rs7807747_A 38 35.0 0 0 40 0 37 0
## rs10405944_G 18 17.5 18 18 0 0 0 18
## rs2331992_G 18 17.5 18 0 0 0 18 18
## rs8093884_A 0 0.0 0 40 0 39 0 0
## rs10412466_G 0 0.0 18 0 0 18 0 18
## rs16825228_G 0 0.0 0 18 18 18 0 18
## rs10063667_A 0 17.5 18 18 18 18 18 0
## rs11150589_A 0 0.0 18 0 18 18 18 18
## rs12005670_A 0 17.5 0 18 0 0 0 18
## rs11257386_A 0 17.5 18 0 0 0 0 18
## rs12598978_A 0 0.0 18 0 18 18 18 18
## rs4821456_G 18 38.0 0 36 36 0 18 0
## rs635070_A 0 17.5 0 0 0 0 38 0
## rs12629469_A 0 0.0 0 0 18 0 18 0
## rs13058433_G 0 0.0 18 0 0 0 0 0
## rs11981000_G 0 0.0 0 0 0 0 0 0
## rs10050725_G 18 0.0 0 0 0 18 0 0
## rs12679812_A 18 0.0 18 18 0 0 18 18
## rs12794303_G 0 0.0 18 18 0 18 18 18
## rs7840855_G 0 17.5 0 18 0 0 0 18
## rs10795908_G 0 0.0 18 0 0 0 18 18
## rs818441_A 0 17.5 18 0 0 18 0 18
## rs2835695_G 0 0.0 0 0 0 0 0 0
## rs4932545_G 0 0.0 0 0 18 0 18 0
## rs11218557_G 0 0.0 0 0 0 18 0 0
## rs9291002_A 0 0.0 18 0 0 0 18 18
## rs742502_G 0 0.0 18 0 0 0 0 0
## rs1732581_A 0 0.0 0 0 18 0 0 0
## rs1016090_G 18 0.0 0 0 0 18 18 0
## rs327826_G 0 0.0 0 39 0 18 0 0
## rs4716858_A 18 17.5 0 0 0 0 0 0
## rs4961252_G 0 0.0 0 0 0 0 0 0
## rs1882153_A 0 0.0 0 0 18 0 0 0
## rs10217194_A 0 0.0 0 0 0 0 0 38
## rs4282978_A 0 0.0 0 0 0 0 0 18
## rs7912364_C 18 0.0 0 18 0 0 18 0
## rs2212736_G 0 0.0 0 0 0 0 0 0
## rs1552046_G 0 0.0 0 0 0 0 0 0
## rs3095301_G 0 0.0 0 0 0 0 0 0
## rs3095302_A 0 0.0 0 0 0 0 0 0
## rs3131003_A 0 0.0 0 0 0 0 0 0
## iter43 iter44 iter45 iter46 iter47 iter48 iter49 iter50
## rs12476415_G 0 17 17.5 18 18 0 0 0
## rs7931183_A 18 0 17.5 39 18 18 0 18
## rs9296990_A 0 0 0.0 18 18 0 40 0
## rs13279576_A 18 17 17.5 18 18 0 18 18
## rs7430710_A 0 0 17.5 18 18 18 18 18
## rs2149733_A 18 17 17.5 18 18 18 0 18
## rs694625_A 0 0 17.5 18 18 0 0 0
## rs2168477_A 18 17 0.0 18 18 18 18 0
## rs10837562_G 18 0 17.5 18 0 0 0 0
## rs7807747_A 0 17 37.0 38 0 0 0 0
## rs10405944_G 18 0 0.0 0 18 18 18 0
## rs2331992_G 18 0 0.0 18 18 18 18 0
## rs8093884_A 0 17 0.0 0 39 18 18 0
## rs10412466_G 18 0 17.5 0 0 0 0 0
## rs16825228_G 0 0 17.5 18 0 0 0 0
## rs10063667_A 0 0 17.5 0 0 0 0 0
## rs11150589_A 18 0 0.0 0 18 0 18 0
## rs12005670_A 0 17 0.0 18 0 18 18 0
## rs11257386_A 18 0 0.0 0 18 18 18 0
## rs12598978_A 18 0 0.0 0 18 0 18 0
## rs4821456_G 0 0 0.0 18 40 40 18 0
## rs635070_A 0 0 35.0 0 0 0 0 0
## rs12629469_A 0 0 0.0 18 0 0 18 18
## rs13058433_G 18 0 17.5 0 0 36 18 18
## rs11981000_G 0 17 17.5 0 0 0 0 0
## rs10050725_G 0 0 17.5 0 0 0 0 0
## rs12679812_A 18 0 17.5 0 0 0 18 0
## rs12794303_G 0 0 0.0 18 0 18 0 0
## rs7840855_G 0 0 0.0 0 0 18 18 0
## rs10795908_G 0 0 0.0 0 18 18 0 18
## rs818441_A 0 0 0.0 0 0 0 18 0
## rs2835695_G 18 0 39.0 0 0 0 0 0
## rs4932545_G 0 0 0.0 18 18 0 0 0
## rs11218557_G 0 0 0.0 0 0 18 0 0
## rs9291002_A 18 0 0.0 0 0 0 0 0
## rs742502_G 0 0 0.0 0 0 18 18 18
## rs1732581_A 0 0 17.5 18 18 18 18 0
## rs1016090_G 0 0 0.0 18 18 0 0 0
## rs327826_G 0 0 0.0 0 0 0 0 0
## rs4716858_A 18 0 0.0 0 18 18 0 0
## rs4961252_G 0 0 0.0 0 0 0 0 18
## rs1882153_A 0 0 17.5 18 18 18 18 0
## rs10217194_A 0 40 0.0 0 18 0 0 0
## rs4282978_A 18 0 0.0 18 0 0 0 0
## rs7912364_C 0 0 0.0 18 0 0 0 0
## rs2212736_G 0 0 38.0 0 0 0 0 0
## rs1552046_G 37 17 0.0 18 0 0 0 0
## rs3095301_G 0 17 17.5 0 0 18 0 0
## rs3095302_A 0 17 17.5 0 0 18 0 0
## rs3131003_A 0 17 17.5 0 0 18 0 0
## iter51 iter52 iter53 iter54 iter55 iter56 iter57 iter58
## rs12476415_G 18 34 18 37 18 0 0 38
## rs7931183_A 18 0 18 0 18 18 18 18
## rs9296990_A 0 0 36 18 0 0 18 18
## rs13279576_A 0 0 18 0 18 18 0 18
## rs7430710_A 0 0 0 18 18 0 0 18
## rs2149733_A 18 0 18 18 18 0 18 18
## rs694625_A 0 0 18 0 18 18 0 0
## rs2168477_A 18 17 18 18 18 0 0 18
## rs10837562_G 18 0 0 18 18 18 18 18
## rs7807747_A 38 0 0 18 18 0 0 40
## rs10405944_G 18 0 0 0 0 0 18 18
## rs2331992_G 18 0 18 18 0 0 0 18
## rs8093884_A 0 17 18 0 0 38 40 0
## rs10412466_G 0 17 37 0 0 0 18 18
## rs16825228_G 0 17 0 36 18 0 0 0
## rs10063667_A 18 17 18 18 18 0 0 18
## rs11150589_A 18 0 18 0 0 18 18 18
## rs12005670_A 0 0 0 0 0 0 18 0
## rs11257386_A 18 0 18 18 18 0 0 18
## rs12598978_A 18 0 18 0 0 18 18 18
## rs4821456_G 18 0 0 18 18 0 0 0
## rs635070_A 18 0 18 18 18 40 0 37
## rs12629469_A 18 0 18 18 18 18 0 18
## rs13058433_G 0 0 0 0 18 18 0 0
## rs11981000_G 18 0 0 0 37 0 36 36
## rs10050725_G 0 0 0 40 0 0 18 18
## rs12679812_A 18 0 0 0 18 18 0 0
## rs12794303_G 0 0 18 0 0 0 0 0
## rs7840855_G 18 17 0 18 0 0 0 18
## rs10795908_G 18 0 18 18 0 0 0 0
## rs818441_A 18 0 0 0 0 0 18 0
## rs2835695_G 39 0 0 0 0 0 0 0
## rs4932545_G 0 17 0 18 0 0 0 0
## rs11218557_G 0 17 0 0 0 0 18 0
## rs9291002_A 18 0 0 0 0 0 0 0
## rs742502_G 0 0 0 0 0 18 0 0
## rs1732581_A 0 0 18 0 0 0 0 0
## rs1016090_G 18 0 0 18 0 18 0 0
## rs327826_G 18 0 0 0 0 0 0 0
## rs4716858_A 18 0 0 0 0 18 0 18
## rs4961252_G 0 0 18 0 40 0 0 0
## rs1882153_A 0 0 18 0 0 0 0 0
## rs10217194_A 0 36 0 0 0 0 0 0
## rs4282978_A 0 0 0 18 0 0 0 0
## rs7912364_C 0 0 0 18 0 0 0 0
## rs2212736_G 40 0 0 0 0 0 0 0
## rs1552046_G 0 0 0 0 0 0 18 0
## rs3095301_G 0 0 0 0 0 0 0 0
## rs3095302_A 0 0 0 0 0 0 0 0
## rs3131003_A 0 0 0 0 0 0 0 0
## iter59 iter60 iter61 iter62 iter63 iter64 iter65 iter66
## rs12476415_G 38 37 18 18 36 0 18 17.5
## rs7931183_A 0 18 18 0 18 18 18 17.5
## rs9296990_A 18 39 18 18 0 0 18 39.0
## rs13279576_A 18 18 18 39 0 0 18 17.5
## rs7430710_A 0 18 0 18 18 18 0 0.0
## rs2149733_A 0 18 18 18 18 18 0 0.0
## rs694625_A 18 0 0 0 0 18 39 0.0
## rs2168477_A 0 18 18 18 18 18 18 17.5
## rs10837562_G 18 18 0 0 18 0 18 17.5
## rs7807747_A 0 0 0 40 0 38 0 0.0
## rs10405944_G 0 18 0 18 38 0 0 38.0
## rs2331992_G 18 18 0 18 18 0 18 17.5
## rs8093884_A 0 18 0 0 18 0 18 0.0
## rs10412466_G 0 18 36 0 0 0 18 0.0
## rs16825228_G 36 36 18 18 0 0 18 0.0
## rs10063667_A 0 18 0 0 0 18 0 0.0
## rs11150589_A 18 0 18 0 18 0 18 17.5
## rs12005670_A 0 0 0 18 18 0 37 17.5
## rs11257386_A 18 18 18 18 0 18 18 17.5
## rs12598978_A 18 0 18 0 18 0 18 17.5
## rs4821456_G 0 0 0 0 18 18 18 17.5
## rs635070_A 0 0 0 0 18 18 0 0.0
## rs12629469_A 0 38 0 0 0 0 0 17.5
## rs13058433_G 0 0 0 0 0 0 0 0.0
## rs11981000_G 0 0 18 0 0 0 0 0.0
## rs10050725_G 0 0 0 0 18 0 18 17.5
## rs12679812_A 0 0 0 0 18 0 0 0.0
## rs12794303_G 0 0 0 0 0 0 0 35.0
## rs7840855_G 18 0 0 0 0 0 18 0.0
## rs10795908_G 18 18 0 0 0 18 18 0.0
## rs818441_A 0 0 0 18 18 0 18 0.0
## rs2835695_G 0 0 39 0 0 0 0 0.0
## rs4932545_G 0 0 0 18 0 0 18 0.0
## rs11218557_G 0 18 37 0 0 0 0 0.0
## rs9291002_A 0 18 0 0 0 0 0 36.0
## rs742502_G 0 0 0 0 0 0 0 0.0
## rs1732581_A 18 0 0 18 0 0 0 0.0
## rs1016090_G 0 0 0 0 0 18 0 0.0
## rs327826_G 0 18 0 0 0 0 0 17.5
## rs4716858_A 0 0 0 0 0 0 0 0.0
## rs4961252_G 18 0 0 18 0 18 0 0.0
## rs1882153_A 0 0 0 18 0 0 0 0.0
## rs10217194_A 0 0 0 37 0 0 0 0.0
## rs4282978_A 18 18 0 0 0 0 0 0.0
## rs7912364_C 0 0 0 18 0 0 0 17.5
## rs2212736_G 0 0 0 0 0 0 0 0.0
## rs1552046_G 0 18 0 0 18 0 18 0.0
## rs3095301_G 0 0 18 0 0 0 0 0.0
## rs3095302_A 0 0 18 0 0 0 0 0.0
## rs3131003_A 0 0 18 0 0 0 0 0.0
## iter67 iter68 iter69 iter70 iter71 iter72 iter73 iter74
## rs12476415_G 0 37.5 18 18 18 0 18 40
## rs7931183_A 18 18.0 38 0 18 0 0 18
## rs9296990_A 38 18.0 0 18 0 36 18 0
## rs13279576_A 18 18.0 18 18 18 37 0 0
## rs7430710_A 18 18.0 18 18 0 18 18 0
## rs2149733_A 0 18.0 18 18 18 18 0 0
## rs694625_A 0 40.0 18 18 18 18 18 0
## rs2168477_A 0 18.0 18 18 18 18 0 18
## rs10837562_G 18 18.0 18 18 0 18 18 0
## rs7807747_A 37 39.0 0 39 37 40 0 39
## rs10405944_G 0 18.0 0 0 18 0 18 0
## rs2331992_G 0 18.0 18 18 18 18 0 0
## rs8093884_A 40 18.0 0 0 18 39 40 0
## rs10412466_G 18 18.0 18 0 18 0 0 0
## rs16825228_G 0 37.5 18 18 18 0 0 0
## rs10063667_A 18 18.0 18 0 18 18 0 0
## rs11150589_A 18 18.0 0 0 0 0 0 0
## rs12005670_A 18 18.0 18 18 0 18 0 0
## rs11257386_A 0 0.0 18 18 0 18 0 18
## rs12598978_A 18 18.0 0 0 0 0 0 0
## rs4821456_G 0 0.0 0 38 18 18 0 38
## rs635070_A 0 0.0 0 0 38 0 0 0
## rs12629469_A 18 0.0 18 0 0 0 0 37
## rs13058433_G 18 36.0 0 0 0 0 0 0
## rs11981000_G 0 0.0 18 0 0 0 0 0
## rs10050725_G 18 0.0 0 0 0 18 0 36
## rs12679812_A 18 0.0 0 0 18 18 0 0
## rs12794303_G 18 0.0 39 18 0 18 0 18
## rs7840855_G 0 0.0 18 0 0 0 18 0
## rs10795908_G 0 0.0 18 0 0 18 18 0
## rs818441_A 0 18.0 0 18 0 0 0 18
## rs2835695_G 0 0.0 0 0 0 18 0 18
## rs4932545_G 0 0.0 0 0 0 0 18 18
## rs11218557_G 0 0.0 0 0 18 0 0 0
## rs9291002_A 18 0.0 0 18 0 0 0 18
## rs742502_G 18 18.0 0 0 0 0 0 0
## rs1732581_A 0 18.0 18 0 18 0 0 0
## rs1016090_G 0 0.0 0 0 0 18 18 0
## rs327826_G 0 0.0 0 0 0 18 0 18
## rs4716858_A 18 18.0 0 0 0 0 0 0
## rs4961252_G 0 0.0 18 0 0 0 0 18
## rs1882153_A 0 18.0 18 0 18 0 0 0
## rs10217194_A 18 0.0 0 0 0 0 0 0
## rs4282978_A 0 0.0 0 0 0 0 18 18
## rs7912364_C 18 18.0 0 0 0 0 0 0
## rs2212736_G 0 0.0 0 0 0 18 0 18
## rs1552046_G 0 0.0 0 0 40 0 0 0
## rs3095301_G 0 0.0 0 18 0 18 0 0
## rs3095302_A 0 0.0 0 18 0 18 0 0
## rs3131003_A 0 0.0 0 18 0 18 0 0
## iter75 iter76 iter77 iter78 iter79 iter80 iter81 iter82
## rs12476415_G 18 37 18 38 0 18 36 18
## rs7931183_A 18 18 18 0 18 40 18 0
## rs9296990_A 18 0 0 18 18 18 0 0
## rs13279576_A 18 18 40 18 18 37 18 0
## rs7430710_A 0 0 18 0 18 18 18 18
## rs2149733_A 0 0 18 18 0 18 18 18
## rs694625_A 0 39 0 0 40 18 18 0
## rs2168477_A 18 0 18 18 0 18 18 18
## rs10837562_G 18 18 0 0 18 18 0 0
## rs7807747_A 0 40 0 0 0 0 0 18
## rs10405944_G 18 0 18 0 18 18 0 36
## rs2331992_G 37 18 18 0 18 0 38 18
## rs8093884_A 18 0 0 0 0 0 0 0
## rs10412466_G 0 0 37 18 18 18 18 0
## rs16825228_G 18 36 18 36 0 18 18 18
## rs10063667_A 0 0 0 0 0 18 18 18
## rs11150589_A 0 0 18 18 18 0 0 0
## rs12005670_A 18 0 18 0 0 0 0 18
## rs11257386_A 0 18 18 0 0 0 0 18
## rs12598978_A 0 0 18 18 18 0 0 0
## rs4821456_G 0 0 0 18 0 0 0 18
## rs635070_A 0 18 0 0 0 0 18 0
## rs12629469_A 18 18 0 0 0 0 0 18
## rs13058433_G 0 0 0 0 18 0 0 0
## rs11981000_G 0 0 0 0 0 18 0 0
## rs10050725_G 0 0 0 0 0 36 0 0
## rs12679812_A 0 0 18 0 18 0 0 18
## rs12794303_G 0 0 0 0 0 18 18 0
## rs7840855_G 0 0 0 0 0 18 0 0
## rs10795908_G 0 0 0 18 0 0 0 0
## rs818441_A 18 0 0 0 0 0 0 0
## rs2835695_G 0 0 0 39 0 18 18 18
## rs4932545_G 18 0 0 0 0 0 0 18
## rs11218557_G 36 0 0 0 0 0 0 0
## rs9291002_A 0 0 18 0 18 0 18 0
## rs742502_G 0 0 0 0 18 0 0 0
## rs1732581_A 0 18 18 0 18 0 18 0
## rs1016090_G 0 0 0 18 0 18 0 0
## rs327826_G 0 0 0 0 0 0 0 0
## rs4716858_A 0 18 0 0 0 0 0 0
## rs4961252_G 0 18 0 0 0 0 18 0
## rs1882153_A 0 18 18 0 18 0 18 0
## rs10217194_A 40 0 0 0 0 0 0 0
## rs4282978_A 0 0 18 18 0 0 18 0
## rs7912364_C 18 0 0 0 0 0 18 0
## rs2212736_G 0 0 0 37 0 18 18 18
## rs1552046_G 0 0 0 0 0 0 0 0
## rs3095301_G 18 0 0 18 0 18 0 18
## rs3095302_A 18 0 0 18 0 18 0 18
## rs3131003_A 18 0 0 18 0 18 0 18
## iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90
## rs12476415_G 0 0 0 36 0.0 18 0 18
## rs7931183_A 18 18 18 37 17.5 18 18 39
## rs9296990_A 18 18 18 18 0.0 36 40 18
## rs13279576_A 18 0 0 18 17.5 18 18 18
## rs7430710_A 18 0 18 18 0.0 18 18 18
## rs2149733_A 0 0 18 18 17.5 0 18 18
## rs694625_A 0 0 0 18 0.0 18 0 0
## rs2168477_A 18 18 18 0 0.0 18 0 18
## rs10837562_G 18 18 0 18 17.5 18 18 18
## rs7807747_A 0 0 0 0 0.0 0 0 0
## rs10405944_G 18 18 0 18 35.0 0 0 0
## rs2331992_G 18 18 18 18 17.5 18 18 0
## rs8093884_A 0 0 0 0 17.5 37 0 0
## rs10412466_G 36 18 0 18 17.5 0 18 0
## rs16825228_G 0 0 0 18 0.0 18 0 0
## rs10063667_A 0 0 0 0 17.5 18 0 18
## rs11150589_A 18 18 0 18 0.0 18 18 18
## rs12005670_A 18 18 18 18 0.0 0 0 0
## rs11257386_A 0 18 18 0 0.0 18 18 36
## rs12598978_A 18 18 0 18 0.0 18 18 18
## rs4821456_G 0 0 18 0 0.0 0 0 0
## rs635070_A 37 0 0 0 0.0 18 0 0
## rs12629469_A 0 18 18 0 0.0 18 0 37
## rs13058433_G 18 18 18 18 0.0 0 0 0
## rs11981000_G 18 39 0 0 0.0 0 0 0
## rs10050725_G 0 0 0 0 0.0 0 36 18
## rs12679812_A 18 18 0 18 17.5 0 0 0
## rs12794303_G 18 0 0 0 17.5 0 0 0
## rs7840855_G 18 0 18 0 17.5 0 0 18
## rs10795908_G 0 0 18 0 0.0 18 0 0
## rs818441_A 18 18 0 0 17.5 0 0 0
## rs2835695_G 0 0 0 0 0.0 0 0 0
## rs4932545_G 0 0 18 0 0.0 0 18 18
## rs11218557_G 0 0 0 0 17.5 0 18 0
## rs9291002_A 0 0 18 18 0.0 0 0 0
## rs742502_G 0 18 18 0 0.0 0 0 0
## rs1732581_A 0 0 18 0 0.0 0 18 18
## rs1016090_G 0 0 18 0 17.5 0 18 18
## rs327826_G 0 0 0 0 39.0 18 0 0
## rs4716858_A 0 0 18 0 0.0 0 18 0
## rs4961252_G 0 0 0 0 0.0 0 0 0
## rs1882153_A 0 0 18 0 0.0 0 18 0
## rs10217194_A 0 0 0 0 0.0 0 0 18
## rs4282978_A 0 0 0 0 0.0 0 0 0
## rs7912364_C 0 18 0 18 0.0 0 0 0
## rs2212736_G 0 0 0 0 0.0 0 0 0
## rs1552046_G 0 0 0 0 0.0 0 0 0
## rs3095301_G 0 37 0 0 17.5 0 0 18
## rs3095302_A 0 37 0 0 17.5 0 0 18
## rs3131003_A 0 37 0 0 17.5 0 0 18
## iter91 iter92 iter93 iter94 iter95 iter96 iter97 iter98
## rs12476415_G 18 18 0 36 38 0 18 18
## rs7931183_A 0 18 18 0 18 0 18 18
## rs9296990_A 37 36 18 18 0 18 18 18
## rs13279576_A 18 18 0 18 40 18 18 18
## rs7430710_A 18 18 18 0 18 0 18 0
## rs2149733_A 18 18 18 18 18 0 0 18
## rs694625_A 36 18 36 0 0 0 18 0
## rs2168477_A 18 18 0 18 18 0 0 18
## rs10837562_G 18 0 0 18 0 18 18 18
## rs7807747_A 0 0 39 0 0 0 0 0
## rs10405944_G 0 0 0 18 0 18 18 0
## rs2331992_G 0 18 0 0 0 39 0 18
## rs8093884_A 0 0 0 40 0 0 36 0
## rs10412466_G 18 0 18 18 0 0 0 18
## rs16825228_G 18 18 0 18 0 0 18 18
## rs10063667_A 0 18 0 18 18 0 18 0
## rs11150589_A 18 0 18 0 0 0 18 0
## rs12005670_A 18 0 0 18 18 18 0 18
## rs11257386_A 0 0 0 0 0 18 0 0
## rs12598978_A 18 0 18 0 0 0 18 0
## rs4821456_G 0 18 0 38 0 18 0 18
## rs635070_A 0 0 0 37 18 0 0 0
## rs12629469_A 18 18 0 0 0 18 0 18
## rs13058433_G 18 0 18 0 18 36 0 0
## rs11981000_G 18 18 0 18 0 37 18 0
## rs10050725_G 0 0 0 0 0 0 0 0
## rs12679812_A 0 18 0 18 0 0 18 18
## rs12794303_G 0 0 18 0 0 18 18 0
## rs7840855_G 0 0 0 0 0 18 0 18
## rs10795908_G 0 0 0 0 0 18 0 0
## rs818441_A 18 0 0 0 18 0 0 18
## rs2835695_G 0 0 18 39 18 0 0 39
## rs4932545_G 0 0 18 0 0 0 0 0
## rs11218557_G 0 0 0 0 18 0 40 37
## rs9291002_A 0 18 0 0 0 0 0 0
## rs742502_G 18 0 18 0 18 18 0 0
## rs1732581_A 0 0 0 0 0 0 0 0
## rs1016090_G 18 0 0 18 0 0 0 18
## rs327826_G 0 37 0 0 0 0 0 0
## rs4716858_A 0 0 0 0 0 18 0 0
## rs4961252_G 0 0 18 0 18 0 0 0
## rs1882153_A 0 0 0 0 0 0 0 0
## rs10217194_A 40 0 0 0 18 0 0 0
## rs4282978_A 0 0 0 18 18 0 0 0
## rs7912364_C 18 18 0 0 0 0 0 18
## rs2212736_G 0 0 18 0 18 0 0 38
## rs1552046_G 0 0 18 0 18 0 0 0
## rs3095301_G 0 0 0 18 0 0 0 0
## rs3095302_A 0 0 0 18 0 0 0 0
## rs3131003_A 0 0 0 18 0 0 0 0
## iter99 iter100 total_rank
## rs12476415_G 18 0 1566.0
## rs7931183_A 38 18 1549.0
## rs9296990_A 0 0 1548.5
## rs13279576_A 18 0 1521.5
## rs7430710_A 18 0 1276.5
## rs2149733_A 18 18 1220.5
## rs694625_A 0 0 1211.5
## rs2168477_A 18 18 1202.0
## rs10837562_G 0 0 1167.5
## rs7807747_A 0 0 1140.0
## rs10405944_G 0 0 1035.0
## rs2331992_G 0 0 1034.5
## rs8093884_A 0 0 1020.5
## rs10412466_G 0 0 958.5
## rs16825228_G 18 0 919.0
## rs10063667_A 0 0 900.0
## rs11150589_A 0 18 899.0
## rs12005670_A 18 18 899.0
## rs11257386_A 0 0 881.0
## rs12598978_A 0 18 881.0
## rs4821456_G 0 36 830.5
## rs635070_A 0 18 744.5
## rs12629469_A 0 0 723.0
## rs13058433_G 0 18 683.5
## rs11981000_G 18 0 673.5
## rs10050725_G 0 0 664.5
## rs12679812_A 0 0 646.5
## rs12794303_G 0 0 632.0
## rs7840855_G 18 18 609.0
## rs10795908_G 0 0 593.5
## rs818441_A 0 0 592.5
## rs2835695_G 0 0 584.0
## rs4932545_G 0 18 539.0
## rs11218557_G 0 0 536.5
## rs9291002_A 0 18 524.0
## rs742502_G 18 18 504.0
## rs1732581_A 18 0 485.5
## rs1016090_G 0 0 485.0
## rs327826_G 0 0 470.0
## rs4716858_A 0 18 449.5
## rs4961252_G 0 0 439.0
## rs1882153_A 18 0 431.5
## rs10217194_A 0 0 415.0
## rs4282978_A 0 0 414.0
## rs7912364_C 0 0 413.0
## rs2212736_G 0 0 411.0
## rs1552046_G 0 0 401.0
## rs3095301_G 0 0 377.0
## rs3095302_A 0 0 377.0
## rs3131003_A 0 0 377.0write.table(gen_features_comp2_final,file="Comp2_GEN_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
phen_features_comp1_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),phen_features_comp1)
rownames(phen_features_comp1_final)<-phen_features_comp1_final$GENE
phen_features_comp1_final$GENE<-NULL
phen_features_comp1_final[is.na(phen_features_comp1_final)]<-0
phen_features_comp1_final$total_rank<-rowSums(phen_features_comp1_final)
phen_features_comp1_final<-phen_features_comp1_final[order(-phen_features_comp1_final$total_rank),]
print(head(phen_features_comp1_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10 iter11
## BMI 4 3 4 4 4 4 4 4 4 4 4
## SI 3 4 2 3 3 3 3 3 2 2 3
## Age 2 2 1 2 2 2 2 2 3 3 2
## Sex 1 1 3 1 1 1 1 1 1 1 1
## iter12 iter13 iter14 iter15 iter16 iter17 iter18 iter19 iter20 iter21
## BMI 4 4 4 4 4 4 3 4 4 4
## SI 2 3 3 3 3 3 4 3 3 3
## Age 3 1 2 2 1 2 1 2 2 1
## Sex 1 2 1 1 2 1 2 1 1 2
## iter22 iter23 iter24 iter25 iter26 iter27 iter28 iter29 iter30 iter31
## BMI 4 4 4 3 4 4 3 4 4 4
## SI 3 3 3 4 3 3 4 3 3 1
## Age 2 1 1 2 2 2 2 2 1 3
## Sex 1 2 2 1 1 1 1 1 2 2
## iter32 iter33 iter34 iter35 iter36 iter37 iter38 iter39 iter40 iter41
## BMI 4 4 4 4 4 4 4 4 3 4
## SI 3 3 3 3 3 3 3 3 4 3
## Age 2 1 2 2 2 2 2 2 2 1
## Sex 1 2 1 1 1 1 1 1 1 2
## iter42 iter43 iter44 iter45 iter46 iter47 iter48 iter49 iter50 iter51
## BMI 4 4 4 4 4 4 4 4 4 4
## SI 3 3 3 3 2 3 2 3 3 3
## Age 2 2 1 2 1 2 3 2 2 2
## Sex 1 1 2 1 3 1 1 1 1 1
## iter52 iter53 iter54 iter55 iter56 iter57 iter58 iter59 iter60 iter61
## BMI 3 4 4 4 4 4 4 4 4 4
## SI 4 3 2 3 3 3 3 3 3 3
## Age 1 1 1 2 2 2 1 2 2 1
## Sex 2 2 3 1 1 1 2 1 1 2
## iter62 iter63 iter64 iter65 iter66 iter67 iter68 iter69 iter70 iter71
## BMI 3 4 4 4 3 4 4 4 4 4
## SI 4 3 2 3 4 3 2 3 3 3
## Age 2 2 3 2 2 1 1 2 2 2
## Sex 1 1 1 1 1 2 3 1 1 1
## iter72 iter73 iter74 iter75 iter76 iter77 iter78 iter79 iter80 iter81
## BMI 4 4 4 4 4 3 4 4 4 4
## SI 2 3 2 2 3 4 3 3 3 2
## Age 3 2 3 3 2 1 2 2 2 3
## Sex 1 1 1 1 1 2 1 1 1 1
## iter82 iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90 iter91
## BMI 4 4 4 3 4 4 4 4 4 4
## SI 3 3 3 4 3 2 3 3 2 3
## Age 2 2 2 2 1 3 2 2 1 1
## Sex 1 1 1 1 2 1 1 1 3 2
## iter92 iter93 iter94 iter95 iter96 iter97 iter98 iter99 iter100
## BMI 4 4 4 3 4 4 4 4 3
## SI 2 2 3 4 2 3 3 3 4
## Age 3 3 1 2 3 2 2 2 2
## Sex 1 1 2 1 1 1 1 1 1
## total_rank
## BMI 388
## SI 292
## Age 190
## Sex 130write.table(phen_features_comp1_final,file="Comp1_PHEN_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")
phen_features_comp2_final<-Reduce(function(x,y) merge(x,y,by="GENE",all=TRUE),phen_features_comp2)
rownames(phen_features_comp2_final)<-phen_features_comp2_final$GENE
phen_features_comp2_final$GENE<-NULL
phen_features_comp2_final[is.na(phen_features_comp2_final)]<-0
phen_features_comp2_final$total_rank<-rowSums(phen_features_comp2_final)
phen_features_comp2_final<-phen_features_comp2_final[order(-phen_features_comp2_final$total_rank),]
print(head(phen_features_comp2_final,50))## iter1 iter2 iter3 iter4 iter5 iter6 iter7 iter8 iter9 iter10 iter11
## Sex 3 2 2 4 4 4 3 3 4 3 3
## Age 4 1 4 1 1 2 4 4 1 4 2
## SI 1 3 3 3 3 3 2 2 3 1 4
## BMI 2 4 1 2 2 1 1 1 2 2 1
## iter12 iter13 iter14 iter15 iter16 iter17 iter18 iter19 iter20 iter21
## Sex 1 2 3 1 3 4 4 4 4 4
## Age 4 1 1 4 4 3 3 2 3 1
## SI 3 4 4 3 2 2 1 3 1 2
## BMI 2 3 2 2 1 1 2 1 2 3
## iter22 iter23 iter24 iter25 iter26 iter27 iter28 iter29 iter30 iter31
## Sex 4 4 4 3 4 1 3 4 1 4
## Age 1 3 3 4 3 2 4 2 4 3
## SI 3 1 1 2 2 4 2 3 3 2
## BMI 2 2 2 1 1 3 1 1 2 1
## iter32 iter33 iter34 iter35 iter36 iter37 iter38 iter39 iter40 iter41
## Sex 3 3 4 3 4 4 3 2 1 4
## Age 4 4 1 4 3 1 4 3 2 3
## SI 2 2 3 2 2 2 2 4 4 2
## BMI 1 1 2 1 1 3 1 1 3 1
## iter42 iter43 iter44 iter45 iter46 iter47 iter48 iter49 iter50 iter51
## Sex 3 2 4 2 3 4 1 3 4 3
## Age 4 4 3 3 4 3 4 1 1 4
## SI 1 3 2 4 1 2 2 4 3 2
## BMI 2 1 1 1 2 1 3 2 2 1
## iter52 iter53 iter54 iter55 iter56 iter57 iter58 iter59 iter60 iter61
## Sex 3 4 2 4 3 3 2 3 2 4
## Age 4 1 4 1 2 4 4 4 4 3
## SI 1 3 3 3 4 1 3 2 3 1
## BMI 2 2 1 2 1 2 1 1 1 2
## iter62 iter63 iter64 iter65 iter66 iter67 iter68 iter69 iter70 iter71
## Sex 1 4 2 4 4 3 3 4 3 4
## Age 4 3 3 3 3 4 1 3 4 2
## SI 3 2 4 2 1 2 4 2 1 3
## BMI 2 1 1 1 2 1 2 1 2 1
## iter72 iter73 iter74 iter75 iter76 iter77 iter78 iter79 iter80 iter81
## Sex 3 4 3 4 4 3 2 4 3 4
## Age 2 1 4 3 1 1 4 2 4 1
## SI 4 2 2 2 3 2 3 3 1 3
## BMI 1 3 1 1 2 4 1 1 2 2
## iter82 iter83 iter84 iter85 iter86 iter87 iter88 iter89 iter90 iter91
## Sex 4 3 3 4 4 2 4 4 3 4
## Age 1 4 4 1 3 4 3 1 4 2
## SI 3 2 2 2 1 1 2 2 1 3
## BMI 2 1 1 3 2 3 1 3 2 1
## iter92 iter93 iter94 iter95 iter96 iter97 iter98 iter99 iter100
## Sex 3 3 2 2 3 1 3 4 4
## Age 2 2 4 1 4 4 4 3 1
## SI 4 4 3 3 2 3 1 2 2
## BMI 1 1 1 4 1 2 2 1 3
## total_rank
## Sex 313
## Age 279
## SI 241
## BMI 167write.table(phen_features_comp2_final,file="Comp2_PHEN_FEATURES.txt",col.names=TRUE,row.names=TRUE,quote=FALSE,sep="\t")We can perform a final integration on the top ranked features and visualize their connections via e.g. network analysis:
expr_features_comp1_final<-read.delim("Comp1_EXPR_FEATURES.txt",header=TRUE,sep="\t")
expr_features_comp2_final<-read.delim("Comp2_EXPR_FEATURES.txt",header=TRUE,sep="\t")
meth_features_comp1_final<-read.delim("Comp1_METH_FEATURES.txt",header=TRUE,sep="\t")
meth_features_comp2_final<-read.delim("Comp2_METH_FEATURES.txt",header=TRUE,sep="\t")
gen_features_comp1_final<-read.delim("Comp1_GEN_FEATURES.txt",header=TRUE,sep="\t")
gen_features_comp2_final<-read.delim("Comp2_GEN_FEATURES.txt",header=TRUE,sep="\t")
phen_features_comp1_final<-read.delim("Comp1_PHEN_FEATURES.txt",header=TRUE,sep="\t")
phen_features_comp2_final<-read.delim("Comp2_PHEN_FEATURES.txt",header=TRUE,sep="\t")
#inclusion_cutoff<-0.3
#features_expr1<-vector()
#for(i in rownames(expr_features_comp1_final))
#{
# if(sum(expr_features_comp1_final[i,]==0) < inclusion_cutoff*N_repeat)
# {
# features_expr1<-append(features_expr1,i)
# }
#}
#features_expr2<-vector()
#for(i in rownames(expr_features_comp2_final))
#{
# if(sum(expr_features_comp2_final[i,]==0) < inclusion_cutoff*N_repeat)
# {
# features_expr2<-append(features_expr2,i)
# }
#}
features_expr1<-rownames(expr_features_comp1_final)[1:50]
features_expr2<-rownames(expr_features_comp2_final)[1:50]
print("Gene expression features to keep:")## [1] "Gene expression features to keep:"print(unique(c(features_expr1, features_expr2)))## [1] "OPRD1" "SLC2A2" "CHL1" "GRAMD2B" "FOXE1" "ELFN1"
## [7] "GABRA2" "ARG2" "TFCP2L1" "BARX1" "CLTRN" "PCOLCE2"
## [13] "RASGRP1" "PLA1A" "COMP" "MPP1" "GLRA1" "GCNT4"
## [19] "HCN4" "PRELP" "RHOT1" "MRO" "GAD1" "NTN1"
## [25] "DACH2" "DCX" "ARL4C" "TBC1D4" "CPXM2" "FFAR4"
## [31] "SLC24A2" "NOTUM" "LRRC2" "F11" "CMTR2" "LSAMP"
## [37] "CACNG5" "NIPAL4" "REEP1" "TAGLN3" "SERPINE2" "CLCF1"
## [43] "C1QTNF1" "TSKU" "KCNA1" "SV2B" "CA5B" "FSTL4"
## [49] "SIX6" "DKK3" "CNTN5" "GNAL" "NEFL" "SULF1"
## [55] "TIAM1" "NXPH3" "TSHR" "SHISAL1" "PTCHD4" "SFTPA1"
## [61] "SYT1" "KIAA0319" "FSTL5" "CTSZ" "LRRTM2"X.expr_selected_features<-subset(expr,select=unique(c(features_expr1, features_expr2)))
#features_meth1<-vector()
#for(i in rownames(meth_features_comp1_final))
#{
# if(sum(meth_features_comp1_final[i,]==0) < inclusion_cutoff*N_repeat)
# {
# features_meth1<-append(features_meth1,i)
# }
#}
#features_meth2<-vector()
#for(i in rownames(meth_features_comp2_final))
#{
# if(sum(meth_features_comp2_final[i,]==0) < inclusion_cutoff*N_repeat)
# {
# features_meth2<-append(features_meth2,i)
# }
#}
features_meth1<-rownames(meth_features_comp1_final)[1:50]
features_meth2<-rownames(meth_features_comp2_final)[1:50]
print("Methylation features to keep:")## [1] "Methylation features to keep:"print(unique(c(features_meth1, features_meth2)))## [1] "cg02988288" "cg02966936" "cg07175985" "cg14527110" "cg12220370"
## [6] "cg13566279" "cg14490520" "cg03770217" "cg06184251" "cg25934997"
## [11] "cg04577129" "cg25979005" "cg09467248" "cg17826980" "cg21165486"
## [16] "cg02736232" "cg13336515" "cg11515284" "cg26767974" "cg05627498"
## [21] "cg09449232" "cg13176806" "cg14534405" "cg22364465" "cg15275625"
## [26] "cg11743000" "cg04255401" "cg06749277" "cg27044597" "cg24196354"
## [31] "cg03220447" "cg21533994" "cg03726357" "cg08248985" "cg12451325"
## [36] "cg04934500" "cg07270865" "cg15630265" "cg26079959" "cg13970113"
## [41] "cg13090941" "cg26445440" "cg27539060" "cg19484548" "cg24486540"
## [46] "cg09216797" "cg00970981" "cg24794608" "cg12164242" "cg03622758"
## [51] "cg13544025" "cg27179424" "cg22152677" "cg12084792" "cg14228710"
## [56] "cg13559778" "cg07523470" "cg16901379" "cg08571304" "cg04684637"
## [61] "cg12546646" "cg20836795" "cg20189782" "cg27051815" "cg12747056"
## [66] "cg07935632" "cg14679463" "cg17802766"X.meth_selected_features<-subset(meth,select=unique(c(features_meth1, features_meth2)))
#features_gen1<-vector()
#for(i in rownames(gen_features_comp1_final))
#{
# if(sum(gen_features_comp1_final[i,]==0) < inclusion_cutoff*N_repeat)
# {
# features_gen1<-append(features_gen1,i)
# }
#}
#features_gen2<-vector()
#for(i in rownames(gen_features_comp2_final))
#{
# if(sum(gen_features_comp2_final[i,]==0) < inclusion_cutoff*N_repeat)
# {
# features_gen2<-append(features_gen2,i)
# }
#}
features_gen1<-rownames(gen_features_comp1_final)[1:50]
features_gen2<-rownames(gen_features_comp2_final)[1:50]
print("Genotype features to keep:")## [1] "Genotype features to keep:"print(unique(c(features_gen1, features_gen2)))## [1] "rs13279576_A" "rs7931183_A" "rs10837562_G" "rs9296990_A"
## [5] "rs2331992_G" "rs12476415_G" "rs7430710_A" "rs11257386_A"
## [9] "rs2149733_A" "rs2168477_A" "rs10412466_G" "rs694625_A"
## [13] "rs11150589_A" "rs16825228_G" "rs12005670_A" "rs12598978_A"
## [17] "rs10405944_G" "rs12629469_A" "rs10063667_A" "rs8093884_A"
## [21] "rs10795908_G" "rs4821456_G" "rs13058433_G" "rs7807747_A"
## [25] "rs12679812_A" "rs11981000_G" "rs10050725_G" "rs4716858_A"
## [29] "rs7840855_G" "rs818441_A" "rs4282978_A" "rs635070_A"
## [33] "rs12794303_G" "rs9291002_A" "rs4932545_G" "rs742502_G"
## [37] "rs1016090_G" "rs1732581_A" "rs750064_G" "rs4961252_G"
## [41] "rs933881_G" "rs7327037_G" "rs1882153_A" "rs2835695_G"
## [45] "rs11218557_G" "rs3095301_G" "rs3095302_A" "rs3131003_A"
## [49] "rs7725574_C" "rs7912364_C" "rs327826_G" "rs10217194_A"
## [53] "rs2212736_G" "rs1552046_G"X.gen_selected_features<-subset(gen,select=unique(c(features_gen1, features_gen2)))
X.phen_selected_features<-phen
data<-list(expr=X.expr_selected_features, meth=X.meth_selected_features,
gen=X.gen_selected_features, phen=X.phen_selected_features)
design=matrix(0.1, ncol=length(data), nrow=length(data), dimnames=list(names(data),names(data)))
diag(design)=0
design["expr","meth"]<-0.1
design["meth","expr"]<-0.1
design["meth","phen"]<-0.01
design["phen","meth"]<-0.01
design["expr","gen"]<-0.01
design["gen","expr"]<-0.01
design["meth","gen"]<-0.01
design["gen","meth"]<-0.01
ncomp=2
list.keepX = list("expr"=c(30,30), "meth"=c(30,30), "gen"=c(10,10), "phen"=c(4,4))
res = block.splsda(X=data,Y=as.factor(T2D$T2D),ncomp=ncomp,keepX=list.keepX,design=design,
scheme="horst",mode="regression",init="svd.single",near.zero.var=TRUE)## Design matrix has changed to include Y; each block will be
## linked to Y.plotIndiv(res,legend=TRUE,title="Human Pancreatic Islets: Individual Omics",ellipse=FALSE,ind.names=TRUE,cex=3)
plotArrow(res,ind.names=TRUE,legend=TRUE,title="Human Pancreatic Islets: Consensus Across Omics")
plotLoadings(res, comp = 1, contrib = 'max', method = 'median')
plotLoadings(res, comp = 2, contrib = 'max', method = 'median')
plotDiablo(res, ncomp = 1)
plotDiablo(res, ncomp = 2)
plotVar(res,var.names=TRUE,style='graphics',legend=TRUE,pch=c(16,17,18,19),cex=c(0.8,0.8,0.8,0.8),col=c('blue','red2',"darkgreen","cyan"))
circosPlot(res,cutoff=0.7,line=FALSE,size.variables=0.5)
cimDiablo(res,margins=c(11,18))
network(res,blocks=c(1,2),cex.node.name=0.6,color.node=c('blue','red2'),breaks=NULL)
network(res,blocks=c(1,3),cex.node.name=0.6,color.node=c('blue','darkgreen'),breaks=NULL)
network(res,blocks=c(1,4),cex.node.name=0.6,color.node=c('blue','cyan'),breaks=NULL)
network(res,blocks=c(2,3),cex.node.name=0.6,color.node=c('red2','darkgreen'),breaks=NULL)
network(res,blocks=c(2,4),cex.node.name=0.6,color.node=c('red2','cyan'),breaks=NULL)
network(res,blocks=c(3,4),cex.node.name=0.6,color.node=c('darkgreen','cyan'),breaks=NULL)
Finally here is the details on the system on which this document was compiled:
sessionInfo()## R version 3.6.1 (2019-07-05)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.3 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.7.1
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.7.1
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=sv_SE.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=sv_SE.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=sv_SE.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=sv_SE.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] grid stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] RColorBrewer_1.1-2 ROCit_1.1.1 mixOmics_6.8.5
## [4] ggplot2_3.2.1 lattice_0.20-38 MASS_7.3-51.4
## [7] VennDiagram_1.6.20 futile.logger_1.4.3 data.table_1.12.2
## [10] matrixStats_0.54.0
##
## loaded via a namespace (and not attached):
## [1] Rcpp_1.0.2 RSpectra_0.15-0 plyr_1.8.4
## [4] compiler_3.6.1 pillar_1.4.2 formatR_1.7
## [7] futile.options_1.0.1 tools_3.6.1 digest_0.6.20
## [10] evaluate_0.14 tibble_2.1.3 gtable_0.3.0
## [13] pkgconfig_2.0.2 rlang_0.4.0 Matrix_1.2-17
## [16] igraph_1.2.4.1 parallel_3.6.1 yaml_2.2.0
## [19] xfun_0.8 gridExtra_2.3 withr_2.1.2
## [22] stringr_1.4.0 dplyr_0.8.3 knitr_1.24.5
## [25] tidyselect_0.2.5 ellipse_0.4.1 glue_1.3.1
## [28] R6_2.4.0 rARPACK_0.11-0 rmarkdown_1.15.1
## [31] reshape2_1.4.3 tidyr_0.8.3 corpcor_1.6.9
## [34] purrr_0.3.2 lambda.r_1.2.3 magrittr_1.5
## [37] scales_1.0.0 htmltools_0.3.6 assertthat_0.2.1
## [40] colorspace_1.4-1 labeling_0.3 stringi_1.4.3
## [43] lazyeval_0.2.2 munsell_0.5.0 crayon_1.3.4